In next-generation 6G Internet-of-Things (IoT) networks, semantic communication has emerged as a key paradigm that transforms raw data into high-level feature representations, thereby reducing communication overhead while enhancing interpretability. When combined with federated learning (FL), these semantic embeddings enable decentralized model training without centralizing raw data, preserving user privacy, and supporting large-scale collaboration. However, semantic features may inadvertently encode sensitive information or act as adversarial triggers, introducing new privacy risks that current unlearning techniques fail to address. To overcome this challenge, we propose Selective Semantic Feature Unlearning (SSFU), a novel framework that performs unlearning at the feature level rather than at the client level. SSFU employs an ensemble-based risk scoring mechanism to identify high-risk latent components, followed by gradient ascent and semantic masking to remove their influence. Unlike existing methods that depend on costly retraining or full client exclusion, SSFU preserves benign semantic knowledge and allows training to continue with minimal disruption. The framework guarantees bounded convergence, and empirical results on benchmark datasets show that SSFU effectively eliminates sensitive features while maintaining predictive accuracy. SSFU thus represents a robust, privacy-preserving FL framework tailored for semantic communication in 6G IoT systems.

Underwater acoustic communication (UAC) is one of the core technologies for the Internet of Underwater Things (IoUT). Channel estimation (CE) is crucial for achieving reliable UAC performance. However, existing underwater acoustic CE methods involve a trade-off between computational overhead and estimation accuracy. To relieve this issue, this paper proposes an efficient and high-precision CE algorithm. Based on compressed sensing theory, the algorithm first obtains an on-grid delay estimate via orthogonal matching pursuit (OMP). Subsequently, we optimize the delay estimation result beyond the grid constraint using an anadromic gradient descent (AGD) algorithm combined with the Armijo backtracking line search approach. The simulation results demonstrate that the proposed AGD-Armijo algorithm achieves comparable CE performance to existing same type of off-grid CE algorithms, while improving the iterative convergence rate by approximately 52.7%. Furthermore, to address the pseudo-path estimation problem caused by off-grid delay errors during the on-grid estimation stage, we propose a two-stage optimization off-grid channel estimation (TSO-OGCE) method. The TSO-OGCE can effectively suppress pseudo-paths and achieve reliable estimation performance by introducing a single-path off-grid optimization step. We have demonstrated the feasibility and effectiveness of the above methods through field experiments at Songhua Lake.

Money laundering is a financial crime that obscures the origin of illicit funds, necessitating the development and enforcement of anti-money laundering (AML) policies by governments and organizations. The proliferation of mobile payment platforms and smart IoT devices has significantly complicated AML investigations. As payment networks become more interconnected, there is an increasing need for efficient real-time detection to process large volumes of transaction data on heterogeneous payment systems by different operators such as digital currencies, cryptocurrencies and account-based payments. Most of these mobile payment networks are supported by connected devices, many of which are considered loT devices in the FinTech space that constantly generate data. Furthermore, the growing complexity and unpredictability of transaction patterns across these networks contribute to a higher incidence of false positives. While machine learning solutions have the potential to enhance detection efficiency, their application in AML faces unique challenges, such as addressing privacy concerns tied to sensitive financial data and managing the real-world constraint of limited data availability due to data regulations. Existing surveys in the AML literature broadly review machine learning approaches for money laundering detection, but they often lack an in-depth exploration of advanced deep learning techniques—an emerging field with significant potential. To address this gap, this paper conducts a comprehensive review of deep learning solutions and the challenges associated with their use in AML. Additionally, we propose a novel framework that applies the least-privilege principle by integrating machine learning techniques, codifying AML red flags, and employing account profiling to provide context for predictions and enable effective fraud detection under limited data availability. Specifically, our approach defines AML-relevant financial profile characteristics and risk indicators to contextualize transactions and assess their associated risks. The proposed context-risk-predict AML (CRP-AML) model demonstrates notable success, achieving an F1 score of 82.51% on the minority class and nearly doubling the performance of other pattern detection models when the proportion of money laundering records in the dataset drops as low as 0.0005.

The cognitive satellite-terrestrial network (CSTN) has emerged as a transformative architecture for enabling ubiquitous global connectivity, yet its broadcast nature and heterogeneous service demands pose critical security challenges against increasingly sophisticated wiretap threats. This paper proposes a novel reconfigurable intelligent surface (RIS)-assisted secure sparse code multiple access (SCMA) framework in CSTN, which aims to maximize the achievable secrecy rate by jointly optimizing the transmit beamforming, RIS reflection matrix, and SCMA codebook configuration while satisfying power constraints at the satellite and base station and meeting the quality-of-service demands of legitimate users. Specifically, a realistic RIS model incorporating coupled phase-amplitude constraints is considered for practical deployment scenarios. To solve the above non-convex optimization problem in dynamic environments, an intelligent decision-making mechanism based on a modified multi-agent two-delay deep deterministic (MMTD3) algorithm is developed to effectively decouple continuous beam control and discrete codebook selection, and provide a new paradigm for AI-driven cross-domain security optimization in CSTN. Simulation experiments demonstrate that the proposed framework outperforms existing benchmarks in key metrics including convergence, reward values, and secrecy rate, highlighting the framework’s potential for supporting ubiquitous security and massive heterogeneous service demands in CSTN.

The integration of large-scale foundation models with physical embodiments has led to significant advancements in robotics termed Generative Physical Artificial Intelligence (GPAI). These agentic AI systems autonomously perceive, reason, and act in complex real-world situations. This survey comprehensively analyzes GPAI systems, focusing on their architectural foundations, current applications, and key limitations. We introduce a taxonomy of five distinct approaches: Robot Foundation Models (RFMs) for cross-platform skill transfer; Vision Language Action Models (VLAs) for end-to-end multi-modal perception and control; Large Behavior Models (LBMs) for human-like movement generation; Diffusion Policy Models (DPMs) for diffusion model-based temporally coherent action generation; and World Foundation Models (WFMs) for physics-compliant simulation and data generation. We examine how these approaches complement each other: WFMs generate training data for VLAs and DPMs, RFMs enable cross-platform deployment of learned policies, while LBMs provide motion priors for natural behavior. Through examples across autonomous vehicles, industrial automation, healthcare robotics, and humanoid systems, we identify significant performance improvements and summarize promising research directions in data-efficient learning, sim-to-real transfer, edge-compatible architectures, and safety frameworks. These insights advance embodied AI for IoT-connected environments where intelligent agents interact with networked sensors, actuators, and edge devices.

With the growing demand for efficient spectrum utilization in integrated radar-communication (IRC) systems, driven by Internet-of-Things (IoT) and fifth-generation (5G) advancements, robust waveform classification techniques have become increasingly critical. This paper introduces TFINet, a cutting-edge deep learning (DL) architecture designed for waveform classification in spectrally congested environments. TFINet leverages time-frequency representations (TFRs) derived from the Smoothing Pseudo-Wigner-Ville Distribution (SPWVD) to improve feature quality and mitigate cross-term interference, enhancing classification accuracy. The network incorporates two key modules: the Dual-Temporal Frequency Extraction (DTFE) and Time-Frequency Selective Downsampling (TFSD). The DTFE module improves feature extraction by decoupling time and frequency features through dual-branch processing, while the TFSD module intelligently reduces dimensionality, preserving essential features without compromising performance. These innovations enable TFINet to balance computational efficiency and classification accuracy, enhancing its suitability for resource-constrained edge devices. On a diverse synthetic dataset of 12 waveform types, TFINet achieves 91.38% overall classification accuracy with 59K parameters and 0.328 ms inference time. Compared to existing deep models, TFINet demonstrates superior performance in both accuracy and efficiency, validating its suitability for practical IRC systems.

In light of the revolutionary requirements of the sixth generation (6G) and beyond wireless networks, reconfigurable intelligent surface (RIS) and rate-splitting multiple access (RSMA) have emerged as pivotal technologies due to their potential for improving spectral efficiency, user fairness, and interference management. This survey explores the theoretical foundations, architectural frameworks, and design strategies of RIS-assisted RSMA, emphasizing the combined adaptability of RIS’s wireless propagation control and RSMA’s multi-user flexibility for dynamic spectrum management. The article first discusses the fundamental concepts of RSMA and RIS technologies. Then, we investigate various enabling technologies for RIS-RSMA networks, highlighting key advancements in interference mitigation, energy efficiency, and security for future networks. Subsequently, some optimization techniques crucial for enhancing RIS-RSMA network performance are presented. Additionally, we examine advanced machine learning (ML) approaches that enable RIS configurations to dynamically adapt to changing network requirements. Techniques such as deep reinforcement learning support real-time adjustments, creating more scalable and resilient RIS-RSMA architectures. Finally, we discuss open research directions for advancing RIS-assisted RSMA in emerging 6G applications. We also consider the potential of advanced ML techniques, including quantum-based ML and large language models, to handle the complexities of large-scale network optimization. This comprehensive survey addresses critical challenges and current advancements. It offers a roadmap for future research in RIS-assisted RSMA networks, paving the way for robust, intelligent, and adaptive 6G wireless communication systems.

This paper presents a deep neural network (DNN)-based resource allocation framework aimed at maximizing energy efficiency (EE) in beam-hopping (BH) low-Earth orbit (LEO) satellite communication systems. Specifically, in BH-LEO satellite systems, it is challenging to solve the joint optimization of time slot scheduling and transmit power control, due to the intrinsic complexity and non-convex nature of the original mixed-integer nonlinear programming formulation. To mitigate this issue, we propose a strategy to decompose the problem into two tractable subproblems: an integer programming model for time slot allocation and a nonlinear programming model for transmit power allocation. For the time slot allocation subproblem, we employ a dueling double deep Q-network (D3QN), combining the strengths of both dueling and double Q-learning techniques to enable stable and efficient decision-making. Then, for the power allocation subproblem, we design a novel unsupervised DNN (UDNN)-based model that estimates spectral efficiency to indirectly determine transmit power, thereby avoiding the difficulties of solving a non-convex optimization problem for EE maximization. Extensive simulation results show that the proposed D3QN and UDNN-based schemes outperform existing iterative and DNN-based approaches in terms of both EE and outage performance, while achieving a significant reduction in computational overhead.

As touchless interaction becomes increasingly important in wearable and ambient computing, gesture-based air handwriting offers a promising input modality, particularly for low-power embedded devices. While vision-based and radar-based systems have achieved high accuracy in gesture recognition, they are often unsuitable for deployment on microcontrollers due to their computational and energy demands. In contrast, IMU-based systems provide a lightweight and privacy-preserving alternative, yet existing research rarely addresses full alphabet recognition or deployment-ready pipelines for resource-constrained environments. This paper proposes a complete TinyML pipeline for inertial-based air handwriting recognition of English alphabets, integrating structured preprocessing of raw IMU data into 2D rasterized gesture images, followed by training and deployment of four lightweight deep learning models: SqueezeNet, EfficientNet-Lite0, ShuffleNetV2, and FastKAN. The models are evaluated under a unified training configuration and subjected to compression techniques including quantization, pruning, and knowledge distillation. Among them, FastKAN demonstrates significant superiority, achieving a test accuracy of 97.4% with a minimal model size of 120 KB and energy consumption as low as 0.0011J per inference after hybrid compression. This work explicitly targets isolated characters (A–Z, a–z); continuous handwriting and word-level recognition are out of scope and left for future work. Extensive evaluations, including confusion matrix analysis, compression benchmarking, and successful deployment on an Arduino Nano 33 BLE Sense, demonstrate the practicality, efficiency, and robustness of the proposed system for real-time TinyML-based handwriting recognition applications.

With the emergence of information overload in the Social Internet of Things (SIoT), personalized recommender systems have become essential for helping users locate the items they need. Effectively modeling the heterogeneous relationships across multiple information sources and weighting them according to their varying importance, especially under sparse social interactions in the SIoT, remains a key challenge. To address this issue, this paper proposes a Multi-source Adaptive Relational Graph Convolutional Network (MARGCN) framework for recommender systems. Useruser and useritem interactions are modeled as two relational graphs, and their embedded features are aggregated using graph convolutional networks (GCNs). A multi-source relationship perception model is designed to dynamically perceive and measure the importance of multiple relationships within the graph structure, thereby enhancing the ability to recognize heterogeneous information. An adaptive information fusion model is then constructed to dynamically integrate representations from different sources through a learnable fusion strategy, avoiding information loss or redundancy caused by simple weighting. Users and items are ultimately represented by aggregating and updating their embeddings via GCNs. Experiments show that compared with the most advanced methods, MARGCN improves the hit rate (HR) and the normalized discounted cumulative gain (NDCG) by 2.66%, 0.52%, and 3.93% in HR@5, HR@10, and HR@15 and by 1.58%, 1.32%, and 3.14% in NDCG@5, NDCG@10, and NDCG@15, respectively.

Accurate and efficient traffic flow prediction is crucial for the increasingly prevalent autonomous driving, enabling more advanced intelligent transportation systems. For this purpose, we propose a novel model termed Meta Guided-Graph Lightweight TimesNet (MGGLTN) to accurately capture the spatio-temporal correlations within traffic flow data, thereby providing precise traffic flow predictions for Connected Vehicles (CVs). Our spatio-temporal information learning architecture features an encoder-decoder backbone, wherein both the encoder and decoder comprise graph convolutional networks coupled with lightweight Times modules. More importantly, we propose a meta guided-graph library, aimed at providing memory queries for time-varying traffic patterns based on real-world physical spatial information. It efficiently guides the initialization direction of meta guided-graph prototypes, thereby accelerating the convergence speed of model training. Moreover, we introduce depthwise separable convolutions to replace the computationally intensive multi-kernel convolutions in the Times modules, thus significantly reducing computational costs and model parameters while maintaining accuracy. We perform extensive experiments on three public benchmark datasets (i.e., METR-LA, PEMS-BAY, and EXPY-TKY) and conduct comprehensive performance evaluations compared to both baseline models and state-of-the-art models. The findings demonstrate the superior performance of our model across all three datasets of varying spatial scales, highlighting the potential of this model to provide precise traffic guidance for CVs.

This paper addresses trajectory optimization, resource allocation, and access management in a multi-unmanned aerial vehicle (UAV) assisted collaborative mobile edge computing network for low-altitude economy. In the network, UAVs collaborate to compute offloaded tasks and improve fairness among time-varying UAV battery levels. The objective of this paper is to maximize the network utility defined by the size of successful offloaded tasks, the fairness among the user equipments, and the processing time and the energy consumption of the UAVs. In particular, we consider the time-varying UAV battery model, which affects the energy cost weights of the UAVs. Therefore, we propose a heuristic optimization framework which integrates utility partitioning two stage matching (UPTSM) algorithm and variables constrained whale optimization algorithm (VC-WOA). The UPTSM algorithm decomposes the original optimization problem into two sub-problems and models them as the bipartite graph matching problems. The VC-WOA achieves the search for legal solutions by limiting the variables which violate the task processing time constraints. Simulation results demonstrate the effectiveness of the proposed heuristic optimization framework in speeding up the convergence and improving the fairness among the UAV battery levels.

This paper addresses a problem of event-triggered state estimation for a linear time-varying Gaussian system over the Internet of Underwater Things (IoUT), where the IoUT is a hybrid topology including underwater acoustic wireless sensors and surface wireless network. Distributed state estimation aims to reconstruct the system state using noisy measurements and local neighbor information, both of which are transmitted via the IoUT. However, IoUT is subject to limited energy and communication bandwidth. Each node, especially applied in underwater case, selectively transmits necessary data to maintain a minimum communication load, and thus to improve energy efficiency and prolong network lifetime. To achieve this goal, we design two event-triggered strategies for typical types of wireless communication channels, of which one channel is used to transmit the local posterior information pair of filter and the other is used to transmit measurement of sensor. Then, based on the covariance intersection fusion rule and the event-triggered strategies, we develop a novel consensus-based distributed state estimator with dual event-triggered communication in a recursive form. Further, after guaranteeing the network connectivity and system collective observability constraints, we derive the uniformly mean-square upper bound of the estimation error of each node. Finally, we provide an example about underwater target tracking to illustrate the effectiveness of the proposed approach.

The vast number of devices and the complexity of requirements present significant challenges in ensuring the security of Non-Terrestrial Internet of Things (NT-IoT). Although existing studies have proposed methods like to defend against data theft and network interference attacks, there is still a need for more in-depth research on detecting data-level attacks in NTNs. Moreover, the vast and diverse nature of network traffic presents significant challenges in traffic modeling and feature extraction. Hypergraph neural networks have gained considerable attention because of capabilities in data modeling and feature extraction. However, most existing hypergraph neural networks are tailored for specific applications and are not adaptable to the detection of malicious encrypted traffic. To address these challenges, we firstly propose a hypergraph neural network-based malicious encrypted traffic detection framework to enhance the resilience of NT-IoT, enabling attack detection across unmanned aerial vehicles, base stations and satellites. Then, we introduce a Multidimensional Encrypted Traffic HyperGraph Network (METHGN). METHGN models the encrypted traffic from network, connection and time dimensions using hypergraph and uses hypergraph convolution network to extracts and fuse features. We conducted comparative experiments on IoT and The Onion Router Network encrypted traffic datasets for different classification tasks. Extensive experiments demonstrate the effectiveness and superiority of our approach.

Resource management is one of the challenges in satellite networks due to their high mobility, wide coverage, long propagation distances, and stringent constraints on energy, communication, and computation resources. Traditional resource allocation approaches rely only on hard and rigid system performance metrics. Meanwhile, incentive mechanisms, which are based on game theory and auction theory, investigate systems from the "economic" perspective in addition to the "system" perspective. Particularly, incentive mechanisms are able to take into account rationality and other behavior of human users into account, which guarantees benefits/utility of all system entities, thereby improving the scalability, adaptability, and fairness in resource allocation. This paper presents a comprehensive survey of incentive mechanism design for resource management in satellite networks. The paper covers key issues in the satellite networks, such as communication resource allocation, computation offloading, privacy and security, and coordination. We conclude with future research directions including learning-based mechanism design for satellite networks.

In this paper, we investigate the outage probability of a multi-tier dual-hop terrestrial-low earth orbit (LEO) satellite-geostationary earth orbit (GEO) satellite hybrid wireless communication system. The system comprises multi-tier LEOs and one GEO act as relays in the uplink, which help the terrestrial ground station (S) transmit information to the terrestrial destination (D). In uplink transmission, we introduce a one-dimensional hardcore point process to model different altitudes of LEOs’ different tiers. We also use a generalized selection combining technique to achieve a trade-off between maximum ratio combining and selection combining. In downlink, GEO offers the maximum coverage to randomly distributed D. Moreover, the independent identically distributed Nakagami-m fading and shadowed Rician distribution are brought to model the different channels. Finally, Monte-Carlo simulations are presented to affirm the precision and accuracy of the derived analytical models and the proposed analysis. This framework offers crucial insights for system designers and network operators, enabling the optimization of resource allocation, relay strategies, and overall reliability in terrestrial-satellite hybrid networks.

Robust Federated Learning (RoFL) extends traditional federated learning, not only by enabling multiple clients to collaboratively train a shared model under the coordination of an edge server, but also by incorporating client-side defense mechanisms (e.g., adversarial training) to defend against adversarial attacks while preserving data privacy. However, recent studies have shown that RoFL also remains vulnerable to the challenges posed by non-independent and identically distributed (non-IID) data distributions across heterogeneous clients, which can degrade overall model generalization and robustness. To mitigate this challenge, in this paper, we propose a novel RoFL framework, called RoFLCCA, to address non-IID challenges while defending against adversarial attacks. In particular, we first introduce a local classifier calibration mechanism that utilizes feature-level augmentation to mitigate the effects of non-IID data. By incorporating global class-wise feature statistics, each client can adjust its classifier using synthetic features derived from these shared representations. Second, we propose a calibrated classifier-guided global adversarial alignment strategy, which enforces consistency between augmented and adversarial predictions to improve robustness. Simulation results demonstrate the effectiveness of the proposed RoFLCCA, which consistently outperforms existing robust federated baselines across different datasets and settings. On average, it achieves a 7.07% improvement in clean accuracy and a 4.71% gain in adversarial robustness, highlighting its ability to enhance both generalization and defense against adversarial threats.

Wi-Fi Channel State Information (CSI) has become a widely studied modality for device-free sensing as it captures fine-grained wireless channel variations that can be mapped to human motion and presence while avoiding the explicit visual disclosure typical of vision-based systems. CSI-based pipelines have been explored for human activity and gesture recognition, fall detection, gait analysis, pose-related inference, and indoor localization. Despite strong results in controlled settings, practical deployment remains difficult due to measurement noise, sensitivity to environmental dynamics, multi-user interference, and system-level constraints in data acquisition and real-time processing. This article surveys machine learning methods forWi-Fi CSI sensing and analyzes more than 65 representative models, connecting algorithmic design choices with implementable end-to-end system design. We introduce a hierarchical taxonomy that organizes the literature into classical machine learning approaches, deep learning architectures, and hybrid strategies. Beyond modeling, we describe the full sensing pipeline- from hardware and network interface card (NIC) selection to software tools, antenna configuration, and signal conditioning- highlighting the design trade-offs that affect robustness and reproducibility. We further compare methods across major application domains and summarize open challenges in generalization to dynamic environments, multi-user separation, and resource-efficient inference. Finally, we outline research directions toward robust generalization, scalable deployment, and privacy-aware learning to support broader real-world adoption.

Accurate segmentation and classification of brain tumors from Magnetic Resonance Imaging (MRI) are critical for effective diagnosis and treatment planning. This paper proposes a novel framework for brain tumor segmentation and classification using deep learning. The segmentation model is based on a modified U-Net architecture, called Residual Feature Pyramids U-Net with Attention (RFAU-Net), which incorporates residual blocks to enhance training depth, attention mechanisms to focus on relevant features, and a feature pyramid module to improve segmentation of small and complex tumor regions. To address class imbalance and pixel degradation during training, we introduce a combined loss function (CL) that integrates Weighted Focal Loss (WFL), assigning higher weights to minority classes and reducing the influence of majority classes. The model is evaluated on two publicly available datasets, achieving state-of-the-art performance with a segmentation accuracy of 97%, a Dice Similarity Coefficient (DSC) of 92.5%, and an Intersection over Union (IoU) of 92%. For tumor classification, we employ a Multi-Headed Convolutional Neural Network (MHCNN), achieving 99.8% accuracy in classifying the MGMT methylation status. These results demonstrate the superiority of the RFAU-Net model over traditional U-Net and RESU-Net architectures, particularly in handling small tumor regions and class imbalance. Additionally, a user-friendly web API is developed to classify brain tumors into MGMT methylated and unmethylated categories, enabling efficient integration of this model into clinical practice for improved diagnosis and treatment of gliomas.

Vehicular metaverses, blending traditional vehicular networks with metaverse technology, are expected to revolutionize fields such as autonomous driving. As virtual intelligent assistants in vehicular metaverses, Artificial Intelligence (AI) agents empowered by large language models can create immersive 3D virtual spaces for passengers to enjoy on-board vehicular applications and services. To provide users with seamless and engaging virtual interactions, resource-limited vehicles offload AI agents to RoadSide Units (RSUs) with adequate communication and computational capabilities. Due to the mobility of vehicles and the limited coverage of RSUs, AI agents need to migrate from one RSU to another. However, potential network attacks pose significant challenges to ensuring reliable and efficient AI agent migration. In this paper, we first explore specific network attacks, including traffic-based attacks (i.e., DDoS attacks) and infrastructure-based attacks (i.e., malicious RSU attacks). Then, we model the AI agent migration process as a Partially Observable Markov Decision Process (POMDP) and apply multi-agent proximal policy optimization algorithms to mitigate DDoS attacks. In addition, we propose a trust assessment mechanism to counter malicious RSU attacks. Numerical results demonstrate that the proposed solutions effectively defend against these network attacks and reduce the total latency of AI agent migration by approximately 12.8%.

This letter proposes a distributed path selection algorithm based on the meta multi-agent proximal policy optimization (Meta-MAPPO). The algorithm leverages transferable knowledge to achieve faster and more stable policy optimization in dynamic satellite networks. We integrate meta-learning into the MAPPO framework, equipping agents with rapid adaptation capabilities and enhancing convergence efficiency through experience sharing. Simulation results on a 96-satellite Walker–Delta constellation demonstrate that the proposed framework achieves at least a 5% reduction in average end-to-end delay, maintains zero packet loss, and converges faster, demonstrating its efficiency and robustness in dynamic satellite network environments.

The boom in telemedicine and digital healthcare has spurred a surge in demand for medical image transmission, especially in remote areas with limited bandwidth, imposing a heavy burden on communication systems. To address the challenge of efficient transmission of massive medical images, this paper proposes a semantic communication-based solution called medical image joint source channel coding (Med-JSCC). Our motivation stems from the fact that during clinical diagnosis, medical professionals predominantly focus on regions of interest (ROI), i.e., critical regions, while paying relatively less attention to non-region of interest (NROI). This inspires us to adopt a differentiated processing strategy. Specifically, we first design a mask-guided feature processing module, where the mask generated by the large medical image segmentation model (e.g., MedSAM-2) identifies ROI-relevant and ROI-irrelevant semantic features. On this basis, a differentiated processing strategy is proposed to balance transmission efficiency and diagnostic reliability. Furthermore, the proposed Med-JSCC integrates an adaptive transmission module, including variable-length coding and a channel adaptive unit (CAU). The former can assign transmission rates to semantic features based on a learned entropy model, while the latter improves the robustness against channel variations by recalibrating semantic features based on channel parameters. Experimental results on dental and chest X-ray datasets demonstrate that our method effectively improves transmission efficiency while preserving diagnostically critical information in medical images.

The energy optimization and demand side management (DSM) of Internet of Things (IoT)-enabled microgrids are being transformed by generative artificial intelligence, such as large language models (LLMs). This paper explores an integration of LLMs into energy management, and emphasizes their roles in automating the optimization of DSM strategies with Internet of Electric Vehicles (IoEV) as a representative example of the Internet of Vehicles (IoV). We investigate challenges and solutions associated with DSM and explore new opportunities presented by leveraging LLMs. Then, we propose an innovative solution that enhances LLMs with retrieval-augmented generation for automatic problem formulation, code generation, and customizing optimization. The results demonstrate the effectiveness of our proposed solution in charging scheduling and optimization for electric vehicles, and highlight our solution’s significant advancements in energy efficiency and user adaptability. This work shows LLMs’ potential in energy optimization of the IoT-enabled microgrids and promotes intelligent DSM solutions.

The recent advancements in large language models (LLMs) have significantly enhanced language understanding and content generation capabilities. However, the deployment of LLMs on resource-constrained Internet of Things (IoT) devices remains challenging due to their substantial computational and storage requirements. To address this issue, we propose a novel LLM pruning method, termed structurally-aware adaptive pruning (SAAP), to reduce computational and storage costs for LLMs while maintaining model performance. Specifically, SAAP first leverages maximum likelihood estimation to calibrate traditional structural importance metrics for LLM pruning. Next, it employs a Bayesian fusion approach to address the predictive uncertainty in multi-granularity metrics, enabling accurate assessments of structural importance for LLMs. Then, SAAP introduces a cross-layer importance alignment mechanism based on quantile mapping, which normalizes layer-wise importance scores to ensure consistent pruning from a global perspective. Furthermore, SAAP develops an efficient block-wise fine-tuning strategy for enhancing the performance of the LLM after pruning. To validate the effectiveness of SAAP, we conduct extensive experiments on nine open-source LLMs across two representative tasks—language modeling and zero-shot classification. Experimental results show that SAAP consistently outperforms several baseline methods, achieving accuracy improvements of 2.5%, 2.63%, and 2.44% on LLaMA-7B, Vicuna-7B, and LLaMA-13B when the pruning ratio is 50%. Finally, SAAP is implemented on a testbed—NVIDIA Jetson AGX Orin 32GB Developer Kit. Test results demonstrate that compared to the foundation LLM, SAAP enhances the inference speed by 86.86% at a pruning ratio of 50%, highlighting its potential for practical deployment on resource-constrained IoT devices.

Large Artificial Intelligence Models (LAMs) possess powerful learning capabilities and are regarded as key technologies for addressing communication challenges in the future sixth-generation (6G) wireless networks. However, their massive parameters make them difficult to deploy on computation resource-constrained end nodes. Recently, large-small model collaboration has been extensively studied, but most works assume homogeneous computational resources across end nodes. This assumption neglects the heterogeneity among nodes, potentially causing significant performance degradation or even system failures due to improper resource allocation and task partitioning. To address this challenge, we propose a large-small model collaboration framework that accounts for heterogeneous computational resources and limited wireless communication bandwidth. In this proposed framework, end nodes are responsible for data collection and local inference using small models. They also cooperate with the edge server that provides large model inference and model update. We design a joint optimization strategy that considers data transmission optimization and transmission resource allocation. The primary objective of this strategy is to enhance the inference accuracy of the framework by maximizing the mean average precision (mAP). Furthermore, we derive a closed-form lower bound for the mAP of the proposed framework. Simulations based on object detection experiments demonstrate that the proposed framework significantly outperforms existing frameworks under different communication bandwidths and data scales.

The channel state information (CSI) acquisition plays a pivotal role in cell-free (CF) massive multiple-input-multi-output (mMIMO) systems. However, conventional pilot-based channel estimation incurs prohibitive overhead costs as user density and mobility increase. To address this, we propose a multi-slot alternating estimation–prediction (MAEP) framework, which leverages temporal correlation to predict future CSI directly and thereby drastically reduce pilot overhead. The efficacy of the proposed framework hinges on prediction accuracy. Inspired by the remarkable modeling capabilities of large language models (LLMs) and their demonstrated efficacy in cross-modal applications, we introduce an LLM-driven channel predictor termed frequency-temporal alignment with LLM (FTAlign-LLM). FTAlign-LLM bridges the modality gap between CSI and the LLM’s feature space through three key components:(i) a multi-scale CSI attention (MSCA) network for extracting rich spatiotemporal features across frequency and delay domains, (ii) a frequency–temporal feature fusion (FTFF) network that fuses these features and aligns them with the LLM’s feature space, and (iii) the utilization of parameter-efficient fine-tuning for LLM adaptation. Extensive results demonstrate that FTAlign-LLM significantly outperforms benchmarks in prediction accuracy. Concurrently, the MAEP framework achieves substantial improvements in sum spectral efficiency, particularly when a large number of access points are deployed in CF mMIMO systems.

Energy efficiency is of paramount importance for covert integrated sensing and communication (ISAC) networks to ensure sustained operation. In light of the imperfect channel state information (CSI) encountered in practical scenarios, we investigate the energy efficiency of these networks. Taking into account a variety of CSI estimation errors, our algorithm optimizes both sensing and information beamforming design while ensuring a low detection probability by multiple untrusted wardens. The energy-efficient beamforming design is formulated as a non-convex fractional programming problem. First, we establish that the covariance matrices of communication beamforming vectors are rank-one. Subsequently, we exploit this property to transform the original problem into a semi-definite relaxed version. For Gaussian CSI estimation errors, we adopt Bernstein-type inequalities to handle the probability constraints of interception and exploit Dinkelbach’s algorithm to address the nonlinear fractional objective function. For bounded CSI estimation errors, we employ an S-procedure to tackle the non-convex constraints associated with covert communications, followed by a successive convex optimization algorithm to provide an effective solution to the original problem. Extensive simulations confirm the superiority of our proposed algorithms, demonstrating a remarkable performance gain compared with baseline schemes adopting existing approaches. Specifically, deploying a larger number of antenna elements can enhance the energy efficiency of covert ISAC networks, while simultaneously reducing the system’s total power consumption. Furthermore, the sensing beam power threshold and the outage probability of covertness serve as important trade-off parameters in covert ISAC networks.

Covert communications provide a stronger privacy protection than cryptography and physical-layer security (PLS). However, previous works on covert communications have implicitly assumed the validity of channel reciprocity, i.e., wireless channels remain constant or approximately constant during their coherence time. In this work, we investigate covert communications in the presence of a disco RIS (DRIS) deployed by the warden Willie, where the DRIS with random and time-varying reflective coefficients acts as a “disco ball”, introducing time-varying fully-passive jamming (FPJ). Consequently, the channel reciprocity assumption no longer holds. The DRIS not only jams the covert transmissions between Alice and Bob, but also decreases the error probabilities of Willie’s detections, without either Bob’s channel knowledge or additional jamming power. To quantify the impact of the DRIS on covert communications, we first design a detection rule for the warden Willie in the presence of time-varying FPJ introduced by the DRIS. Then, we define the detection error probabilities, i.e., the false alarm rate (FAR) and the missed detection rate (MDR), as the monitoring performance metrics for Willie’s detections, and the signal-to-jamming-plus-noise ratio (SJNR) as a communication performance metric for the covert transmissions between Alice and Bob. Based on the detection rule, we derive the detection threshold for the warden Willie to detect whether communications between Alice and Bob is ongoing, considering the time-varying DRIS-based FPJ. Moreover, we conduct theoretical analyses of the FAR and the MDR at the warden Willie, as well as SJNR at Bob, and then present unique properties of the DRIS-based FPJ in covert communications. We present numerical results to validate the derived theoretical analyses and evaluate the impact of DRIS on covert communications.

Due to the scalability and portability, low-altitude intelligent networks (LAINs) are essential in various fields such as surveillance and disaster rescue. However, in LAINs, unmanned aerial vehicles (UAVs) are characterized by the distributed topology and high mobility, thus vulnerable to security threats, which may degrade routing performances for data transmissions. Hence, how to ensure the routing stability and security of LAINs is challenging. In this paper, we focus on the routing with multiple UAV clusters in LAINs. To minimize the damage caused by potential threats, we present the zero-trust architecture with the software-defined perimeter and blockchain techniques to manage the identify and mobility of UAVs. Besides, we formulate the routing problem to optimize the end-to-end (E2E) delay and transmission success ratio (TSR) simultaneously, which is an integer nonlinear programming problem and intractable to solve. Therefore, we reformulate the problem into a decentralized partially observable Markov decision process. We design the multi-agent double deep Q-network-based routing algorithms to solve the problem, empowered by the soft-hierarchical experience replay buffer and prioritized experience replay mechanisms. Finally, extensive simulations are conducted and the numerical results demonstrate that the proposed framework reduces the average E2E delay by 59% and improves the TSR by 29% on average compared to benchmarks, while simultaneously enabling faster and more robust identification of low-trust UAVs.

Despite significant advancements in terrestrial networks, inherent limitations persist in providing reliable coverage to remote areas and maintaining resilience during natural disasters. Multi-tier networks with low Earth orbit (LEO) satellites and high-altitude platforms (HAPs) offer promising solutions, but face challenges from high mobility and dynamic channel conditions that cause unstable connections and frequent handovers. In this paper, we design a three-tier network architecture that integrates LEO satellites, HAPs, and ground terminals with hybrid free-space optical (FSO) and radio frequency (RF) links to maximize coverage while maintaining connectivity reliability. This hybrid approach leverages the high bandwidth of FSO for satellite-to-HAP links and the weather resilience of RF for HAP-to-ground links. We formulate a joint optimization problem to simultaneously balance downlink transmission rate and handover frequency by optimizing network configuration and satellite handover decisions. The problem is highly dynamic and non-convex with time-coupled constraints. To address these challenges, we propose a novel large language model (LLM)-guided truncated quantile critics algorithm with dynamic action masking (LTQC-DAM) that utilizes dynamic action masking to eliminate unnecessary exploration and employs LLMs to adaptively tune hyperparameters. Simulation results demonstrate that the proposed LTQC-DAM algorithm outperforms baseline algorithms in terms of convergence, downlink transmission rate, and handover frequency. We also reveal that compared to other state-of-the-art LLMs, DeepSeek delivers the best performance through gradual, contextually-aware parameter adjustments.

This paper investigates a near-field covert communication system enhanced by an absorptive reconfigurable intelligent surface (ARIS) and a fluid antenna system (FAS), enabling covert transmission to arbitrary receiver locations. By generating near-field spherical waves via large-scale antenna arrays at Alice and ARIS, covert transmission to Bob is enabled while evading detection by Willie. We jointly optimize Alice’s hybrid precoding, ARIS reflection coefficients, and Bob’s active port selection to maximize the worst-case covert transmission rate. We begin by evaluating ARIS’s suitability versus conventional RIS. We demonstrate the asymptotic orthogonality of near-field beam-focusing vectors in the 3D domain for uniform planar arrays, and characterize the beam-focusing behavior in cascaded ARIS-enabled covert transmissions. Additionally, we reveal the channel gain improvement owing to FAS over traditional antenna systems. To solve the coupled non-convex problem, we propose a low-complexity block coordinate descent algorithm. It incorporates Fibonacci search for hybrid precoding, three complexity-performance trade-off strategies for reflection coefficients optimization, and both exhaustive search and linear conic relaxation for active port selection. Finally, we recover precoding via an alternating minimization scheme. Numerical results show that (i) significant improvement of covert transmission is achieved only with both ARIS and FAS, when Bob and Willie are co-located; (ii) the proposed algorithm outperforms near-field and far-field beam alignment schemes without ARIS, as well as beam focusing of full-map zeroing with ARIS, when Bob and Willie share the same reception direction.

Nowadays, Generative AI (GenAI) reshapes numerous domains by enabling machines to create content across modalities. As GenAI evolves into autonomous agents capable of reasoning, collaboration, and interaction, they are increasingly deployed on network infrastructures to serve humans automatically. This emerging paradigm, known as the agentic network, presents new optimization challenges due to the demand to incorporate subjective intents of human users expressed in natural language. Traditional generic Deep Reinforcement Learning (DRL) struggles to capture intent semantics and adjust policies dynamically, thus leading to suboptimality. In this paper, we present LAMeTA, a Large AI Model (LAM)-empowered Two-stage Approach for intent-aware agentic network optimization. First, we propose Intent-oriented Knowledge Distillation (IoKD), which efficiently distills intent-understanding capabilities from resource-intensive LAMs to lightweight edge LAMs (E-LAMs) to serve end users. Second, we develop Symbiotic Reinforcement Learning (SRL), integrating E-LAMs with a policy-based DRL framework. In SRL, E-LAMs translate natural language user intents into structured preference vectors that guide both state representation and reward design. The DRL, in turn, optimizes the generative service function chain composition and E-LAM selection based on real-time network conditions, thus optimizing the subjective Quality-of-Experience (QoE). Extensive experiments conducted in an agentic network with 81 agents demonstrate that IoKD reduces mean squared error in intent prediction by up to 22.5%, while SRL outperforms conventional generic DRL by up to 23.5% in maximizing intent-aware QoE.

Large artificial intelligence (AI) models for wireless communications have demonstrated remarkable success across a range of wireless downstream tasks. However, their high computational overhead, low training efficiency, and limited privacy protection pose significant challenges for deployment on resource-constrained terminal devices. To address this issue, we propose a novel distributed framework that utilizes a three-layer cooperative paradigm to effectively achieve cooperation among agents, namely Multi-agent cooperative Large AI Models for Wireless Communications: MaLAM4Com. However, two key challenges in MaLAM4Com are how to effectively extract knowledge from shared information and how to alleviate the significant complexity arising from high-dimensional information sharing. To address these bottlenecks, we introduce federated distillation and Lyapunov cooperation to achieve robust knowledge transfer and consistent dynamic evolution, enabling the agents to capture the intrinsic structure of wireless channels. Subsequently, we innovatively utilize low-dimensional embeddings to facilitate information sharing among agents, significantly reducing cooperation complexity by up to 94% while enhancing privacy protection. This breaks traditional cooperative paradigms that rely on wireless channels. Moreover, we further introduce dataset distillation to enhance training efficiency by synthesizing elite data instead of directly utilizing raw datasets. Numerical results demonstrate that MaLAM4Com significantly outperforms existing baselines, with gains exceeding 45% under low sampling ratios. Remarkably, low-dimensional embeddings have also shown significant advantages in downstream tasks, reducing inference complexity by over 96%.

This paper explores the energy efficiency (EE) of integrated sensing and communication (ISAC) systems employing massive multiple-input multiple-output (mMIMO) techniques to leverage spatial beamforming gains for both communication and sensing. We focus on an mMIMO-ISAC system operating in an orthogonal frequency-division multiplexing setting with a uniform planar array, zero-forcing downlink transmission, and mono-static radar sensing to exploit multi-carrier channel diversity. By deriving closed-form expressions for the achievable communication rate and Cramér-Rao bounds (CRBs), we are able to determine the overall EE in closed-form. A power allocation problem is then formulated to maximize the system’s EE by balancing communication and sensing efficiency while satisfying communication rate requirements and CRB constraints. Through a detailed analysis of CRB properties, we reformulate the problem into a more manageable form and leverage Dinkelbach’s and successive convex approximation (SCA) techniques to develop an efficient iterative algorithm. A novel initialization strategy is also proposed to ensure high-quality feasible starting points for the iterative optimization process. Extensive simulations demonstrate the significant performance improvement of the proposed approach over baseline approaches. Results further reveal that as communication spectral efficiency rises, the influence of sensing EE on the overall system EE becomes more pronounced, even in sensing-dominated scenarios. Specifically, in the high ω regime of 2 × 10−3, we observe a 16.7% reduction in overall EE when spectral efficiency increases from 4 to 8 bps/Hz, despite the system being sensing-dominated.

Future wireless networks, such as 6G, are envisioned to deliver ultra-reliable, high-quality services with ultra-low latency and dynamic connectivity across heterogeneous environments, driving the adoption of edge–cloud collaborative architectures. Within this paradigm, container-based microservices, with their lightweight, modular, and portable characteristics, offer an effective foundation for scalable and adaptive service provisioning in heterogeneous wireless networks. The layered architecture of microservices facilitates efficient resource management through layer scheduling and caching. However, dynamic service requests and diverse container layers pose major challenges for layer-aware service provisioning in future wireless environments. These includetime-exceeded offline service provisioning, tangled microservice orchestration, andlayer cache redundancy. To address these challenges, we propose Tri-Ring, an asynchronous online provisioning framework for future wireless networks, empowered by large AI models (LAMs). The framework optimizes request dispatching, orchestration, and layer updates across three timescales. At the small timescale, we formulate request dispatching as a linear programming (LP) subproblem. At the medium timescale, the estimator-assessor algorithm manages microservice orchestration, where a diffusion-enhanced prediction model serves as the estimator to predict layer caching strategies. Moreover, submodular optimization serves as the assessor to determine deployment and scheduling. At the large timescale, we introduce the age of layer (AoL) to guide the pruning of infrequently accessed cached layers to reduce storage overhead. Comprehensive evaluations on real-world datasets demonstrates that Tri-Ring outperforms existing baselines, increasing utility by 44.78%, reducing microservice startup time by 78.64%, and optimizing storage resources by 36.38%.

Integrated sensing and communication (ISAC) uses the same software and hardware resources to achieve both communication and sensing functionalities. Thus, it stands as one of the core technologies of 6G and has garnered significant attention in recent years. In ISAC systems, a variety of machine learning models are trained to analyze and identify signal patterns, thereby ensuring reliable sensing and communications. However, considering factors such as communication rates, costs, and privacy, collecting sufficient training data from various ISAC scenarios for these models is impractical. Hence, this paper introduces a generative AI (GenAI) enabled robust data augmentation scheme. The scheme first employs a conditioned diffusion model trained on a limited amount of collected CSI data to generate new samples, thereby enhancing the sample quantity. Building on this, the scheme further utilizes another diffusion model to enhance the sample quality, thereby facilitating the data augmentation in scenarios where the original sensing data is insufficient and unevenly distributed. Moreover, we propose a novel algorithm to estimate the acceleration and jerk of signal propagation path length changes from CSI. We then use the proposed scheme to enhance the estimated parameters and detect the number of targets based on the enhanced data. The evaluation reveals that our scheme improves the detection performance by up to 70%, demonstrating reliability and robustness, which supports the deployment and practical use of the ISAC network.

In this paper, we propose an energy efficient wireless communication system based on fluid antenna relay (FAR) to solve the problem of non-line-of-sight (NLoS) links caused by blockages with considering the physical properties. Driven by the demand for the sixth generation (6G) communication, fluid antenna systems (FASs) have become a key technology due to their flexibility in dynamically adjusting antenna positions. Existing research on FAS primarily focuses on line-of-sight (LoS) communication scenarios, and neglects the situations where only NLoS links exist. To address the issues posted by NLoS communication, we design an FAR-assisted communication system combined with amplify-and-forward (AF) protocol. In order to alleviate the high energy consumption introduced by AF protocol while ensuring communication quality, we formulate an energy efficiency (EE) maximization problem. By optimizing the positions of the fluid antennas (FAs) on both sides of the FAR, we achieve controllable phase shifts of the signals transmitting through the blockage which causes the NLoS link. Besides, we establish a channel model that jointly considers the blockage-through matrix, large-scale fading, and small-scale fading. To maximize the EE of the system, we jointly optimize the FAR position, FA positions, power control, and beamforming design under given constraints, and propose an iterative algorithm to solve this formulated optimization problem. Simulation results show that the proposed algorithm outperforms the traditional schemes in terms of EE, achieving up to 23.39% and 39.94% higher EE than the conventional reconfigurable intelligent surface (RIS) scheme and traditional AF relay scheme, respectively.

Next-generation satellite systems require efficient collaboration in terms of wide area coverage and signal augmentation, enabling intelligent allocation of available wireless resources to ensure the security of information. Meanwhile, machine learning (ML) is widely considered well-suited to massive, real-time data scenarios in satellite communication networks, and graph neural network (GNN) is a specific branch for processing the irregular data within such networks. In this paper, we propose physical layer security for a multi-satellite collaborative (MSC) system involving LEO satellites, users, and eavesdroppers. Specifically, the GNN-based security communication of the MSC (G-MSC-SC) architecture is designed to maximize the secrecy rate. Since heterogeneous and isomorphic methods can effectively solve multi-type node mapping and complex communication problems, the G-MSC-SC architecture is divided into two steps: A heterogeneous graph pruning attention coefficient network (HGPAN) and an isomorphic graph eavesdropper as an auxiliary node network (IGEAN). In the HGPAN architecture, different types of device nodes are embedded in the same dimensional space, addressing the challenge of matching LEO satellites to users. The IGEAN architecture maps user channel state information (CSI) to beamforming (BF) vectors through attention aggregation and an improved loss function. Moreover, the corresponding conventional optimization algorithms are designed as test and comparison baselines. Simulation results show that 1) the G-MSC-SC architecture outperforms neural networks and heuristic algorithms in terms of accuracy and efficiency; 2) as the numbers of users and virtual eavesdroppers increase, the directional alignment between the BF vectors and the LEO satellite-user channels shows an improvement; and 3) with imperfect CSI, the G-MSC-SC architecture still achieves an excellent balance between user secrecy rate and communication rate.

This paper investigates covert prompt transmission for secure and efficient large language model (LLM) services over wireless networks. We formulate a latency minimization problem under fidelity and detectability constraints to ensure confidential and covert communication by jointly optimizing the transmit power and prompt compression ratio. To solve this problem, we first propose a prompt compression and encryption (PCAE) framework, performing surprisal-guided compression followed by lightweight permutation-based encryption. Specifically, PCAE employs a locally deployed small language model (SLM) to estimate token-level surprisal scores, selectively retaining semantically critical tokens while discarding redundant ones. This significantly reduces computational overhead and transmission duration. To further enhance covert wireless transmission, we then develop a group-based proximal policy optimization (GPPO) method that samples multiple candidate actions for each state, selecting the optimal one within each group and incorporating a Kullback-Leibler (KL) divergence penalty to improve policy stability and exploration. Simulation results show that PCAE achieves comparable LLM response fidelity to baseline methods while reducing preprocessing latency by over five orders of magnitude, enabling real-time edge deployment. We further validate PCAE effectiveness across diverse LLM backbones, including DeepSeek-32B, Qwen-32B, and their smaller variants. Moreover, GPPO reduces covert transmission latency by up to 38.6% compared to existing reinforcement learning strategies, with further analysis showing that increased transmit power provides additional latency benefits.

Traditional covert ambient backscatter communication (AmBC) systems suffer from a fundamental throughput limitation governed by the square root law (SRL), restricting reliable covert transmission toO(√n) bits overnchannel uses. To overcome this limitation, we introduce a non-colluding replay node that retransmits ambient radio frequency (RF) signals with randomized power, significantly increasing channel uncertainty faced by an adversarial warden (Willie) while preserving compatibility with low-power AmBC architectures. Through rigorous theoretical analysis, we demonstrate that this approach enables linear scaling of covert throughput without necessitating power reduction or prior knowledge of ambient RF signal characteristics. Furthermore, it guarantees that Willie’s total detection error probability can be driven arbitrarily close to 1, specificallyPFA+PMD= 1 − ϵ for any ϵ > 0, simultaneously achieving an arbitrarily low decoding error probability at the legitimate receiver (Bob). Unlike conventional jamming-based solutions requiring stringent synchronization or complex multi-antenna configurations, our replay mechanism operates independently from covert communication participants, substantially simplifying the decoding architecture for the legitimate receiver and reducing synchronization overhead. By increasing the ambient signal power uncertainty, the proposed architecture provides a robust, scalable framework suitable for high-rate covert communication scenarios in IoT and privacy-sensitive applications, achieving an effective balance among covertness, energy efficiency, and system robustness.

Deep joint source-channel coding (JSCC) has emerged as a promising paradigm for semantic communication, delivering significant performance gains over conventional separate coding schemes. However, existing JSCC frameworks remain vulnerable to physical-layer adversarial threats, such as pilot spoofing and subcarrier jamming, compromising semantic fidelity. In this paper, we propose SecDiff, a plug-and-play, diffusion-aided decoding framework that significantly enhances the security and robustness of deep JSCC under adversarial wireless environments. Different from prior diffusion-guided JSCC methods that suffer from high inference latency, SecDiff employs pseudoinverse-guided sampling and adaptive guidance weighting, enabling flexible step-size control and efficient semantic reconstruction. To counter jamming attacks, we introduce a power-based subcarrier masking strategy and recast recovery as a masked inpainting problem, solved via diffusion guidance. For pilot spoofing, we formulate channel estimation as a blind inverse problem and develop an expectation-minimization (EM)-driven reconstruction algorithm, guided jointly by reconstruction loss and a channel operator. Notably, our method alternates between pilot recovery and channel estimation, enabling joint refinement of both variables throughout the diffusion process. Extensive experiments over orthogonal frequency-division multiplexing (OFDM) channels under adversarial conditions show that SecDiff outperforms existing secure and generative JSCC baselines by achieving a favorable trade-off between reconstruction quality and computational cost. This balance makes SecDiff a promising step toward practical, low-latency, and attack-resilient semantic communications.

Space simultaneous information and power transfer (SSIPT) extends simultaneous wireless information and power transfer (SWIPT) from terrestrial to space-based scenarios for efficient energy utilization beyond the limitations of photovoltaic systems. A large-aperture antenna is required to provide sufficient gain to compensate for the severe path loss caused by the extremely long transmission distance in the SSIPT system. However, most existing antennas employ phased-array (PA) architectures that depend on costly hardware components, making it difficult to achieve the aforementioned requirements under constrained budgets. In this paper, we propose a reconfigurable holographic surface (RHS)-assisted SSIPT system. Specifically, RHSs, which can be implemented entirely with low-cost, commercially available components, offer a promising alternative to conventional PAs for realizing cost-efficient SSIPT. The serial-feed architecture of RHSs introduces radiation power coupling among adjacent elements, which significantly affects the transmission characteristics and invalidates conventional PA-based SWIPT analytical models. To address this issue, we develop a new analytical SSIPT framework that accurately captures the serial coupling effect and design amplitude-controlled beamforming schemes that depart fundamentally from phase-shift-based approaches, which improve rate-energy (R-E) performance. In simulations, we demonstrate that under the same hardware cost, the RHS achieves an expanded R-E region compared with the PA. Therefore, the compact and low-cost characteristics of RHSs make them more suitable for SSIPT scenarios with limited payload and cost.

The success of collaborative task completion among networked devices hinges on the effective selection of trustworthy collaborators. However, accurate task-specific trust evaluation of multi-hop collaborators can be extremely complex. The reason is that their trust evaluation is determined by a combination of diverse trust-related perspectives with different characteristics, including historical collaboration reliability, volatile and sensitive conditions of available resources for collaboration, as well as continuously evolving network topologies. To address this challenge, this paper presents a graph neural network (GNN)-aided distributed agentic AI (GADAI) framework, in which different aspects of devices’ task-specific trustworthiness are separately evaluated and jointly integrated to facilitate multi-hop collaborator selection. GADAI first utilizes a GNN-assisted model to infer device trust from historical collaboration data. Specifically, it employs GNN to propagate and aggregate trust information among multi-hop neighbours, resulting in more accurate device reliability evaluation. Considering the dynamic and privacy-sensitive nature of device resources, a privacy-preserving resource evaluation mechanism is implemented using agentic AI. Each device hosts a large AI model-driven agent capable of autonomously determining whether its local resources meet the requirements of a given task, ensuring both task-specific and privacy-preserving trust evaluation. By combining the outcomes of these assessments, only the trusted devices can coordinate a task-oriented multi-hop cooperation path through their agents in a distributed manner. Experimental results show that our proposed GADAI outperforms the comparison algorithms in planning multi-hop paths that maximize the value of task completion.

The rise of latency-sensitive and bandwidth-intensive services has driven hardware accelerator adoption in cloud networks. Programmable data plane (PDP) switches achieve significant performance gains in high-performance cloud computing but face fixed pipeline constraints that limit flexibility in multi-tenant service function chaining (SFC) with dynamic function compositions. Existing approaches either exhaust resources through redundant embeddings or degrade performance via packet recirculation. This paper presents PBox, a framework enabling flexible SFC orchestration across multiple PDP switches by optimizing network function (NF) execution orders to minimize pipeline traversals-the dominant end-to-end processing delay source. This requires co-designing NF embedding with routing strategies. PBox contributes: (i) an optimized Network Service Header design supporting one-pass matching of multiple NFs through per-bit activation, reducing packet matching overhead by 45-60%; (ii) a nested optimization formulation capturing interdependence between long-term pipeline orchestration and short-term flow routing decisions; and (iii) a sampling-based genetic algorithm with statistical robustness guarantees, achieving fast switch configuration while adapting to dynamic service patterns. Evaluations on BMv2 and Intel Tofino demonstrate 33-79% completion time reduction, 46% capacity increase, and 78% line-rate efficiency, validating cloud-scale deployment potential.

Due to the growing diversity of vertical applications, current integrated sensing and communications (ISAC) technologies in wireless networks remain insufficient to support complex services beyond communications. To this end, future networks are evolving toward an integrated heterogeneous service provisioning (IHSP) platform, which aims to integrate a broad range of heterogeneous services beyond the dual-function scope of ISAC. Nevertheless, this trend intensifies the conflicts among concurrent heterogeneous services under constrained resource sharing. In this paper, we overcome this resource constraint by the joint use of two novel elastic design strategies: compromised service value assessment and flexible multi-dimensional resource sharing. Consequently, we propose a value-prioritized elastic multi-dimensional multiple access (MDMA) mechanism for IHSP. First, we define the compromised Value-of-Service (VoS) metric by incorporating elastic parameters to characterize user-specific tolerance and compromise in response to various performance degradations under constrained resources. This VoS metric serves as the foundation for prioritizing resource sharing among IHSP services with fairness among concurrent competing demands. Next, we adapt the MDMA to elastically multiplex services using appropriate multiple access schemes across different resource domains. This protocol leverages user-specific interference tolerances and cancellation capabilities across different domains to reduce resource-demanding conflicts and co-channel interference within the same domain. Then, we maximize the system’s VoS by jointly optimizing MDMA design and power allocation. Since this problem is non-convex, we propose a monotonic optimization-aided dynamic programming (MODP) algorithm to obtain its optimal solution. Additionally, we develop the VoS-prioritized successive convex approximation (SCA) algorithm to efficiently find its suboptimal solution. Finally, simulations are presented to validate the effectiveness of the proposed designs.

Unmanned aerial vehicles (UAVs) have been applied to various tasks in the low-altitude economy (LAE) with the advantages of high mobility, low costs, and flexible deployment. However, due to the broadcast nature of wireless channels and the increasing number of UAVs, the security of UAV control information and the spectrum resource utilization face significant challenges and threats. Therefore, in this paper, we investigate the secrecy performance of UAV short-packet control information transmission networks based on rate-splitting multiple access (RSMA) with the presence of multiple eavesdroppers. Moreover, we consider and analyze the impacts of both imperfect channel state information (CSI) and successive interference cancellation (SIC) in a more realistic scenario. Considering both large-scale fading and Nakagami-msmall-scale fading, the closed-form expression of the average effective secrecy sum rate is derived utilizing stochastic geometry and the Gauss-Chebyshev quadrature. Considering that the private stream can be concealed within the high-power common stream, an optimization problem is formulated to maximize the common rate by jointly optimizing the blocklength and power allocation coefficients to enhance security. The block coordinate descent (BCD) algorithm is adopted to solve this problem. Finally, simulation results demonstrate the accuracy of the analysis and the effectiveness of the proposed scheme.

In multiple-input multiple-output (MIMO) - orthogonal frequency division multiplexing (OFDM) based communication systems, traditional pilot allocation schemes used for channel estimation may not be optimal for target positioning. This limitation motivates us to design a novel allocation scheme that flexibly fulfills requirements in integrated sensing and communication (ISAC) implementations. To address this, we first establish a unified channel state information (CSI) based ISAC model for single-site indoor positioning in uplink MIMO-OFDM systems. To quantify the impact of resource elements (REs) allocated to pilots—across both subcarrier and OFDM symbol dimensions—on positioning performance, we derive the Cramér-Rao lower bounds (CRLBs) of the target parameters for single-site positioning. Subsequently, we jointly optimize the number of pilot REs in the subcarrier dimension and the OFDM symbol dimension to minimize the squared position error bound (SPEB), while satisfying the requirements for communication capacity and velocity estimation. For the formulated mixed integer nonlinear programming (MINLP) problem, we propose an algorithm based on sequential convex approximation (SCA) and penalty functions to convert the non-convex problem into a convex one for efficient solution. Simulation results demonstrate that the proposed algorithm achieves superior SPEB performance compared to benchmark schemes, thereby maximizing time-frequency resource utilization in single-site indoor positioning systems.

Deep learning (DL)-based models have been widely applied in wireless communication systems with excellent performance. However, most of these models are task- and scenario-specific, exhibiting limited generalization and contributing to increasing complexity and overhead with their deployment in systems. Inspired by the emergent capabilities and strong generalization exhibited by large models (LMs), represented by large language models (LLMs), this paper analyzes the differences between existing DL-based wireless communication models and LLMs, proposing a framework for designing LMs tailored to wireless communications. Building upon this framework, we integrate channel-related tasks of the physical layer into a unified pre-training task, i.e., channel completion, and propose a pre-trained masked channel model (MCM) with different parameter scales ranging from 5 million to 1 billion (B), enabling simultaneous solving of channel state information (CSI) feedback, prediction, and estimation. Additionally, scaling laws on these downstream tasks are derived to guide the design and deployment of MCMs. The formulated scaling laws indicate that the proposed MCM with 1B parameter not only shows no sign of performance saturation on the pre-trained task but also has the potential to enhance performance at larger model sizes. Simulation results demonstrate that the proposed MCM outperforms the existing algorithms across various downstream tasks while exhibiting superior cross-task and cross-scenario generalization capabilities in both simulated and realistic scenarios.

In this paper, we study a sampling-based detection strategy for massive multiple-input multiple-output (MIMO) systems, driven by a modified discrete diffusion model formulated as an analytical, non-learning sampling process. Built upon this framework, the proposed discrete diffusion-based sampling (DDS) algorithm improves decoding performance by leveraging residual-dependent sampling, compared to the independent randomized successive interference cancellation (SIC). Specifically, the modified diffusion model incorporates a shortcut perturbation toward the SIC solution, a forward diffusion step to enhance diversity, and step-wise alignment with the perturbed received signal. Within this framework, the DDS algorithm further adopts one-dimensional discrete Gaussian distribution, involving a reformulated discrete Gaussian noise and an explicitly characterized sampling range, but retains computational complexity amenable to practical deployment. Moreover, we theoretically demonstrate an improved expected decoding radius over randomized SIC. Finally, simulation results based on massive MIMO detection are presented to confirm performance gain of the proposed DDS algorithm.

In this paper, we investigate a Multi-layer Aerial system for GenAI inference at the Edge (MAGE). Therein, ground user equipments (UEs) request image synthesis services from a remote base station (BS) that leverages the Latent Diffusion Model (LDM) for image generation. Multiple Unmanned Aerial Vehicles (UAVs) are deployed to serve the UEs for relaying their images and prompts to the BS. To reduce the communication cost and the computation burden at the BS, the UAVs can partially execute the LDM inference, i.e., an image autoencoder and prompt encoder, and offload the diffusion process task to the BS. In this work, we aim to minimize the BRISQUE scores across all the UEs by jointly optimizing the UAVs' positions, UE-UAV associations, the number of denoising steps at the BS, and offloading strategies of the UAVs. The optimization problem is non-convex, in which the objective function based on BRISQUE scores has no closed-form expression. Due to the fixed exploration strategy of Proximal Policy Optimization (PPO), which limits the policy's adaptability in dynamic environments, this leads to sub-optimal solutions. To address these potential drawbacks, we propose an adaptive exploration strategy that dynamically adjusts the exploration rate based on observed improvements in rewards. Specifically, the exploration capability is controlled by modulating the influence of the entropy bonus according to recent reward gains. Simulations based on the COCO-Stuff datasets show that the proposed scheme outperforms baseline schemes in different terms of BRISQUE score, UAVs' energy consumption, and inference latency. In particular, the proposed scheme reduces the BRISQUE score by up to 20-28.57%, inference energy consumption up to 15.98-30.17%, transmission energy consumption by 15.4-18.5%, and the latency by up to 33.33-43.28% compared to the baseline methods, resulting in higher image quality with a noticeably improved level of perceptual naturalness, improved energy efficiency, as well as substantially faster performance.

This paper proposes a double phase shifter–based hybrid beamforming (DPS-HBF) framework for millimeter-wave NOMA systems, enabling the simultaneous realization of beam steering and beam focusing within a unified analog architecture. By superposing two independent phase-shifter vectors per beam, DPS-HBF flexibly supports heterogeneous near-field and far-field users without requiring full channel state information. To exploit this capability, a hierarchical scheduling framework combining Bitmask Dynamic Programming, Maximum Weight Matching, andk-best Semi-Greedy User Scheduling is developed to balance optimality, scalability, and computational complexity. The proposed design relies solely on low-overhead SINR feedback, making it suitable for practical large-scale deployments. Simulation results show that DPS-HBF consistently outperforms existing hybrid beamforming and orthogonal multiple access baselines in terms of sum-rate and fairness, achieving up to 30–35% throughput gains over the strongest benchmark under moderate-to-high SNR conditions.

Low Earth Orbit (LEO) satellite communications provide uninterrupted coverage and seamless services, which are becoming a crucial element in the Sixth-Generation of wireless communications. However, LEO communications are subject to high path loss and Doppler frequency shift, which presents significant challenges for such large-distance and time-changeable satellite-terrestrial transmission links. Direct Sequence Spread Spectrum (DSSS) has been widely adopted as a robust modulation technique in LEO satellite systems. Traditional DSSS signal detection methods, which rely on 2D searching, fail to effectively acquire the weak uplink signals due to the extremely low signal-to-noise ratio and pronounced channel dynamics. In light of these considerations, this study proposes an algorithm designated as time synchronization-aided signal detection, with the objective of enhancing the signal detection probability in low signal-to-noise ratio and high-mobility communication scenarios. Furthermore, we develop a novel transmission system based on time synchronization, with the objective of reducing the signal detection threshold by minimizing the impact of the Doppler frequency shift and time delay searching ranges. We theoretically analyze performance at varying time synchronization precision, numerical simulations and hardware experiments under diverse conditions demonstrate that, in comparison to the conventional algorithm, time synchronization can enhance the probability of signal detection.

Concurrently supporting heterogeneous services, e.g., sensing and communication (S&C), presents a significant challenge for future wireless networks due to the increasing number of connected devices, limited resources, and the complexity of integrated service provisioning. Furthermore, dynamic network conditions, along with varying heterogeneous needs from coexisting devices, further exacerbate the challenges of traditional rigid system operation, where heterogeneous network services are treated as either entirely independent or fully integrated. This rigid operation neglects the fluctuating gains and costs of the integrated heterogeneous service provisioning. To transform isolated operations into a highly integrated paradigm, this paper proposes a progressive scheme for integrated sensing and communication (ISAC). The scheme elastically adjusts the integration level based on continuously accumulated system state observations, including user demand, resource conditions, and environmental changes, to regulate resource utilization dynamically. Specifically, we present a unified Value of Service (VoS) metric, which adaptively incorporates user service experiences, resource costs, and gains from S&C coupling to guide efficient resource allocation. In addition, building on this progressive integration scheme, we develop a dynamic stage-dependent resource optimization algorithm for bandwidth allocation. Simulation results demonstrate the effectiveness of the proposed integrated framework and algorithm in optimizing resource allocation and maintaining system performance under stringent resource constraints.

Photon counting (PhC) is an effective detection technology for underwater optical wireless communication (OWC) systems. The presence of signal-dependent Poisson shot noise and asynchronous multi-user interference (MUI) complicates the processing of received data signals, hindering the effective signal detection of PhC OWC systems. This paper proposes a novel iterative signal detection method in grant-free, multi-user, underwater PhC OWC systems with signal-dependent Poisson shot noise. We first introduce a new synchronization algorithm with a unique frame structure design. The algorithm performs active user identification and transmission delay estimation. Specifically, the estimation is performed first on a user group basis and then at the individual user level with reduced complexity and latency.We also develop a nonlinear iterative multi-user detection (MUD) algorithm that utilizes a detection window for each user to identify interfering symbols and estimate MUI on a slot-by-slot basis, followed by maximuma-posterioriprobability detection of user signals. Simulations demonstrate that our scheme achieves bit error rates comparable to scenarios with transmission delays known and signal detection perfectly synchronized.

Uncrewed aerial vehicle (UAV) networks are increasingly exposed to widespread and various network attacks due to their fully distributed nature and the limited defensive capabilities of individual devices. Existing defense strategies rely on network connectivity and UAV status information, which overlook information of network traffic. Malicious traffic detection offers a promising solution to achieve fine-grained attack detection. However, the dynamic nature and complexity of UAV networks limit the effectiveness of traditional traffic detection methods. Current approaches either fail to fully exploit the raw characteristics of traffic or do not consider the timeliness requirements of UAV networks. To address these challenges, we propose a novel twin graph encoder neural network, which can extract features of raw traffic bytes for efficient traffic detection. First, we propose a decoupled architecture for model training and inference to enable efficient detection of malicious traffic in UAV networks. Second, we propose a novel modeling method that models traffic as the co-occurrence graph and word frequency graph based on raw bytes. Then, we propose TGE-ETD, a Twin Graph Encoder for Encrypted Traffic Detection. TGE-ETD consists of a set of twin graph encoders that effectively extract intrinsic traffic features from graphs constructed from raw bytes. In addition, TGE-ETD employs a global attention pooling mechanism to effectively distinguish the feature contributions of different bytes. Finally, we conducted extensive experiments on a real UAV traffic dataset and four real-world network traffic datasets. TGE-ETD achieved an improvement of 1%-20% over the baseline methods by reducing the number of parameters by 20 times. Tested on multiple UAV hardware devices, TGE-ETD can achieve millisecond-level traffic detection.

While low-altitude wireless networks (LAWNs) based on uncrewed aerial vehicles (UAVs) offer high mobility, flexibility, and coverage for urban communications, they face severe signal attenuation in dense environments due to obstructions. To address this critical issue, we consider introducing collaborative beamforming (CB) of UAVs and omnidirectional reconfigurable beamforming (ORB) of simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) to enhance the signal quality and directionality. On this basis, we formulate a joint rate and energy optimization problem (JREOP) to maximize the transmission rate of the overall system, while minimizing the energy consumption of the UAV swarm. Due to the non-convex and NP-hard nature of JREOP, we propose a heterogeneous multi-agent collaborative dynamic (HMCD) optimization framework, which has two core components. The first component is a simulated annealing (SA)-based STAR-RIS control method, which dynamically optimizes reflection and transmission coefficients to enhance signal propagation. The second component is an improved multi-agent deep reinforcement learning (MADRL) control method, which incorporates a self-attention evaluation mechanism to capture interactions between UAVs and an adaptive velocity transition mechanism to enhance training stability. Simulation results demonstrate that HMCD outperforms various baselines in terms of convergence speed, average transmission rate, and energy consumption. Further analysis reveals that the average transmission rate of the overall system scales positively with both UAV count and STAR-RIS element numbers.

With the arrival of sixth-generation communication systems, advanced technologies like reconfigurable intelligent surfaces (RIS), integrated sensing and communication (ISAC), and non-orthogonal multiple access (NOMA) are poised to drive a broad range of Internet of Things (IoT) applications. Integrating ISAC into multi-input single-output (MISO) networks calls for a reassessment of performance metrics such as outage probability and sensing rate. Furthermore, a critical challenge is managing heterogeneous user deployments and dynamically adapting to varying user locations while minimizing interference. To address these challenges, this work proposes an innovative multi-sector RIS framework. By dividing the RIS into independently controlled sectors, the system dynamically selects the sector closest to each user. For downlink transmission, a dual-function base station (BS) utilizes NOMA to serve the user clusters and transmit a sensing signal. The RIS dynamically selects the sector closest to the close-proximity user based on their location. To support this, the proposed approach employs a nearest-sector selection strategy centered around a reference close-proximity user. Closed-form approximations for the outage probability are then derived, assuming a blocked direct link between the BS and the users. This framework also enables ISAC by transmitting sensing signals within the selected sector, facilitating both user communication and target detection. We characterize the sensing by the sensing rate, with results showing that increasing RIS elements in the multi-sector design enhances the sensing rate. Overall, the proposed system demonstrates superior performance over traditional simultaneously transmitting and reflecting (STAR)RIS configurations and space division multiple access (SDMA) systems. In particular, the proposed system achieves a gain of 8dB, 12dB and 2dB over SDMA, conventional RIS and STAR-RIS systems, respectively.

This paper investigates signaling by a base station equipped with a dynamic metasurface antenna (DMA) to support the transmission of multi-stream information to multiple near-field users. We consider the joint design of the low-resolution DMA elements’ frequency responses and the baseband precoder to ensure the quality-of-service (QoS) for all users in terms of their rates. First, we develop convex quadratic solver-based iterations of cubic complexity to address the computationally challenging max-min rate optimization problem involving nonsmooth large-scale mixed discrete-continuous optimization. We then opt for the soft max-min rate optimization problem, which involves smooth mixed discrete-continuous optimization, and develop closed-form expression-based iterations of scalable complexity for its computation. The latter approach is not only computationally efficient but also achieves both a high minimum user rate and sum-rate, thereby guaranteeing QoS and high overall network throughput.

With the rapid growth of intelligent aerial-terrestrial applications, enabling collaborative multimodal learning (CML) across heterogeneous data sources, such as aerial images from unmanned aerial vehicles (UAVs) and time-series signals from ground edge devices (EDs), has become essential for achieving reliable intelligence beyond unimodal approaches. However, aerial-terrestrial CML systems face stringent latency requirements, limited energy and computation resources, and vulnerability to adversarial attacks, which are not jointly addressed in existing studies. This paper proposes a wireless aerial-terrestrial CML framework that integrates distributed UAVs and terrestrial EDs with modality-specific encoder training and multimodal fusion at a ground base station (BS). We formulate a latency minimization problem under energy, and security-aware constraints by jointly optimizing UAV trajectories and resource allocation, ED resource allocation, as well as resource allocation of the BS. The framework explicitly incorporates both passive eavesdropping and active interference attacks to ensure secure and robust aerial-terrestrial CML operation. To solve the resulting non-convex latency minimization problem, we develop a simple yet efficient iterative optimization algorithm to find a high-quality optimal solution based on successive convex approximation. Extensive simulation results with real-world datasets demonstrate that the proposed framework significantly outperforms existing training methods in terms of accuracy, loss, and convergence. Moreover, our joint optimization framework achieves up to 94.05% lower latency and stronger robustness against aerial adversaries compared with baseline schemes.

Massive multiple-input multiple-output (MIMO) systems with one-bit analog-to-digital converters (ADCs) face a severe trade-off between hardware efficiency and channel estimation accuracy. While generative adversarial networks (GANs) show promise for this challenge, their deployment is hindered by training instability and mode collapse. To address these issues, we propose ReRpGAN, a novel adversarial learning framework that integrates a regularized relativistic pairing GAN loss and anL1loss within a deep residual network. This architecture effectively stabilizes the training process and prevents mode collapse, enabling precise channel reconstruction from severely quantized signals. Extensive experiments on a realistic ray-tracing channel dataset validate our theoretical claims. Key findings demonstrate that ReRpGAN consistently outperforms conventional GAN-based and deep learning estimators, particularly in challenging scenarios with low signal-to-noise ratios and limited pilot overhead. Furthermore, unlike existing methods that suffer from divergence, ReRpGAN exhibits superior scalability, delivering improved estimation accuracy as the number of base station antennas increases. This work sets a new benchmark for robust, data-driven channel estimation in next-generation wireless systems.

This paper proposes a channel decomposition method and a novel beamforming architecture for line-of-sight (LoS) multi-input multi-output (MIMO) systems with dual continuous apertures (CAPs). Specifically, we develop a three-dimensional (3D) dual-CAP geometric model through orthogonal basis projection, establishing a unified electromagnetic analysis framework for arbitrarily oriented non-coplanar CAPs and enabling consistent 3D wave propagation modeling. Building on this model, we derive the closed-form expression for the effective degrees of freedom (EDoF) of the dual-CAP LoS MIMO system by analyzing spherical wave phase differences via sampling theory. This explicitly connects EDoF to wavelength, propagation distance, and angular rotation. Our proposed channel decomposition method decouples dual-CAP LoS MIMO channels into multiple independent SISO subchannels, which enables a novel beamforming architecture. We implement this architecture through a wavefront degrees of freedom orthogonal subchannel decomposition (WDOSD) algorithm to maximize the achievable rate of the dual-CAP LoS MIMO system. Numerical results demonstrate that: i) both component-wise EDoF and total EDoF can be accurately obtained using our proposed closed-form expressions; ii) under varying transmitter CAP sizes with fixed power, our WDOSD algorithm achieves up to three times performance improvement over the minimum mean-squared error (MMSE) algorithm; and iii) under varying communication distance with fixed angle, the WDOSD algorithm achieves up to two times performance improvement over the MMSE algorithm.

The pervasive threat of jamming attacks, particularly from adaptive jammers capable of optimizing their strategies, poses a significant challenge to the security and reliability of wireless communications. This paper addresses this issue by investigating anti-jamming communications empowered by an active reconfigurable intelligent surface. The strategic interaction between the legitimate system and the adaptive jammer is modeled as a Stackelberg game, where the legitimate user, acting as the leader, proactively designs its strategy while anticipating the jammer’s optimal response. We prove the existence of the Stackelberg equilibrium and derive it using a backward induction method. Particularly, the jammer’s optimal strategy is embedded into the leader’s problem, resulting in a bi-level optimization that jointly considers legitimate transmit power, transmit/receive beamformers, and active reflection. We tackle this complex, non-convex problem by using a block coordinate descent framework, wherein subproblems are iteratively solved via convex relaxation and successive convex approximation techniques. Simulation results demonstrate the significant superiority of the proposed active RIS-assisted scheme in enhancing legitimate transmissions and degrading jamming effects compared to baseline schemes across various scenarios. These findings highlight the effectiveness of combining active RIS technology with a strategic game-theoretic framework for anti-jamming communications.

This paper proposes a robust received signal strength (RSS)-based localization framework for non-cooperative unmanned aerial vehicles. Conventional RSS methods face three fundamental obstacles: susceptibility to heavy-tailed measurement noise, intractable non-convexity, and severe accuracy degradation when target transmission power is unknown. These vulnerabilities present critical security risks to emerging low-altitude economy networks. To overcome these limitations, we propose an integrated joint-estimation architecture. First, a cascaded preprocessing pipeline, combining Gaussian outlier suppression and statistical median weighting, is developed to mitigate multipath-induced biases and minimize variance. Second, an information-theoretic base station (BS) selection mechanism is designed to identify geometrically optimal BSs, thereby exponentially reducing computational overhead in both uniform and random deployment scenarios. Third, the power-unknown problem is reformulated via semidefinite programming, absorbing the unknown parameter into a higher-dimensional convex cone to guarantee global convergence without relying on initial guesses. Extensive Monte Carlo simulations demonstrate that under uniform BS deployment, our strategy achieves sub-10-meter accuracy (approximately 5 m root mean square error) using only 5 selected BSs in typical urban conditions with a path loss exponent of 3. Consequently, this approach delivers a highly accurate and computationally efficient solution for real-time target tracking in complex environments.

Composite fading distributions provide tractable modeling of shadowing and multipath effects, enabling accurate channel characterization and improving communication reliability. Motivated by this, we propose λ-κ-μ shadowed distribution to precisely describe the signal fading behavior caused by the joint impact of shadowing effects and multipath clusters in non-homogeneous channels. Specifically, deterministic expressions for the probability density function, cumulative distribution function, and high-order raw moments are derived, immediately followed by key performance metrics, such as average bit error rate, ergodic capacity, and effective rate. Subsequently, asymptotic analyses of these metrics are conducted in the high signal-to-noise ratio regime to derive simplified expressions that facilitate system evaluation. Furthermore, we systematically analyze the relationship between these expressions and their parameters. The results demonstrate that our proposed λ-κ-μ shadowed distribution possesses good mathematical tractability, with its accuracy validated by Monte Carlo simulations. Additionally, we conduct the truncation error analysis to examine the convergence of the proposed model, and its practical applicability was confirmed through field measurements. More importantly, our proposed λ-κ-μ shadowed distribution subsumes multiple classical distributions as special cases, exhibiting strong flexibility and applicability.

In future 6G networks, mobile edge computing (MEC) is envisioned to offer integrated computing, communication, and storage services at the network edge, enhancing both computational efficiency and communication quality. However, most existing MEC designs neglect the impact of jamming attacks, especially those from intelligent and adaptive jammers. To fill this important research gap, this paper investigates a jamming-resilient MEC framework that aims to improve communication reliability and reduce system delay under adversarial interference. Leveraging the emerging movable antenna (MA) technology, which allows dynamic adjustment of antenna positions and orientations, we propose a novel MA-assisted anti-jamming MEC architecture. Unlike existing works, our model explicitly considers the movement delay caused by MA, which is critical for practical deployment. We jointly optimize the MA positions at both the user equipment (UE) and the base station (BS), BS transmit beamforming, and task offloading ratios to minimize the total system delay. The resulting optimization problem is non-convex and highly coupled. Thus, we develop an efficient algorithm based on penalty dual decomposition (PDD) and successive convex approximation (SCA). Simulation results demonstrate that the proposed scheme significantly outperforms traditional fixed-position antenna (FPA) baselines in terms of jamming resilience and delay minimization, offering new insights into robust MEC system design for 6G networks.

Cooperative-integrated sensing and communication (C-ISAC) networks have emerged as promising solutions for communication and target sensing. However, imperfect channel state information (CSI) estimation and time synchronization (TS) errors degrade performance, affecting communication and sensing accuracy. This paper addresses these challenges by employing movable antennas (MAs) to enhance C-ISAC robustness. We analyze the impact of CSI errors on achievable rates and introduce a hybrid Cramer-Rao lower bound (HCRLB) to evaluate the effect of TS errors on target localization accuracy. Based on these models, we derive the worst-case achievable rate and sensing precision under such errors. We optimize cooperative beamforming, base station (BS) selection factor and MA position to minimize power consumption while ensuring accuracy. We then propose a constrained deep reinforcement learning (C-DRL) approach to solve this non-convex optimization problem, using a modified deep deterministic policy gradient (DDPG) algorithm with a Wolpertinger architecture for efficient training under complex constraints. To the best of our knowledge, this is the first work that jointly integrates TS errors and imperfect CSI into a unified MA-aided cooperative ISAC framework, providing a physically consistent model for both communication and sensing under dual uncertainties. Simulation results show that the proposed method significantly improves system robustness against CSI and TS errors, where robustness mean reliable data transmission under poor channel conditions. These findings demonstrate the potential of MA technology to reduce power consumption in imperfect CSI and TS environments.

Satellite-integrated Internet is capable of providing extensive coverage for massive terrestrial sensing user equipment (UE), facilitating access that satisfies the diverse requirements of multi-type services. However, existing proactive multiple access schemes often induce severe UE collisions, particularly hindering the performance of services with stringent requirements, and thus degrading overall system utility. In this paper, we investigate a utility-oriented satellite-queried system, where rate-splitting multiple access (RSMA) is adopted to support multi-type services with utility guarantees. The utility characteristic is captured by a semantic-empowered metric, termed utility loss of information (UoI), which comprehensively integrates timeliness, service priority, transceiver matching status, and energy consumption. To minimize the average UoI, we propose an adaptive RSMA (A-RSMA) scheme that dynamically adjusts the number of sub-data and power allocation according to the number of accessing UEs. To further improve UoI, we propose an adaptive grouped RSMA (Ag-RSMA) scheme, where the covered UEs are grouped according to their diverse utility requirements. We also introduce a reinforcement learning approach to optimize the dynamic resource scheduling. Simulation results demonstrate that our A-RSMA scheme achieves a lower UoI compared to the state-of-the-art schemes, and the Ag-RSMA scheme satisfies diverse UoI requirements than its non-grouped counterpart.

The explosive growth of mobile data traffic has prompted operators to deploy a large number of base stations (BSs). However, due to the uneven traffic distribution, many BSs remain underutilized or idle during off-peak periods while still consuming substantial amounts of energy. To tackle this issue, we propose a Proactive Optimization-based (PO-based) BS sleeping strategy for large scale scenarios with hundreds of BSs. Specifically, by analyzing the Autocorrelation Function (ACF) of BS traffic in real-world scenarios, we identify multiple potential periods. Guided by this insight, we introduce multi-time-window mechanism and Graph Convolutional Network (GCN), designing Multi-Time-Window Spatio-Temporal Graph Convolutional Network (MTSGCN) to effectively capture the complex spatio-temporal dependencies present large-scale settings. The forecasted results acquired by MTSGCN serve as inputs to a multiple-BSs cooperative sleeping problem with the objective to minimize the total energy consumption. To tackle this huge problem efficiently, we first use K-means++ to divide the large region into several small cooperative clusters and then adopt the Integral Linear Programming (ILP) algorithm to solve each subproblem. Experimental results demonstrate that MTSGCN reduce the forecasting error by 10.9% compared with the state-of-the-art methods. Furthermore, the proposed MTSGCN-ILP algorithm achieves over 20% energy savings gains compared to the other typical strategies.

Diverse and complex wireless interference is one of the most critical threats to modern wireless communication systems. The continuous shift of wireless interference toward higher frequency and wider bandwidth imposes sampling-rate limitations on wireless interference identification (WII). Existing compressed sensing-based WII methods designed for undersampling scenarios suffer from high-complexity signal reconstruction and low identification accuracy caused by fixed sampling strategies. To address these challenges, we propose a multi-domain fusion model which employs domain-specific hybrid sampling to extract interference features for multi-attribute WII without signal reconstruction. Given the respective classification advantages of random and uniform undersampling in time-domain sequences and time–frequency images, this paper proposes a dual-branch architecture to exploit their joint benefits. Specifically, we propose a learnable sparse sampler combined with a Transformer to extract time-domain features in the random undersampling branch. We further prove that the Restricted Isometry Property (RIP)-compliant undersampling largely preserves the feature class discriminability, which motivates the introduction of the RIP loss. In parallel, we propose a multi-scale feature extraction module and a cross-fusion module for dimensionality reduction in the uniform undersampling branch. Subsequently, an attribute correlation-driven graph convolution network is introduced to classify the fused features from both branches, further improving WII performance. Finally, we propose an adaptive multi-domain binary cross-entropy loss and prove that the optimal weight of the RIP loss effectively mitigates gradient conflicts. Experimental results show that the proposed model improves precision by 25.1% over the state-of-the-art, while maintaining effective multi-attribute WII performance at undersampling ratios up to 8.

Cell-free massive multiple-input multiple-output (CF-mMIMO) systems and simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) are considered as promising technologies for enhancing the performance of wireless communication systems. In this paper, we investigate the performance of a STAR-RIS-aided CF-mMIMO system under channel aging, which has been ignored in previous studies. Firstly, we propose a linear minimum mean squared error (LMMSE) aggregated channel estimator and formulate statistical channel state information (CSI) properties for the subsequent system performance analyses. Then, closed-form expressions for the uplink and downlink spectral efficiencies (SEs) of the STAR-RIS-aided CF-mMIMO system under channel aging are explored, where for the uplink, the two-layer large-scale fading decoding (LSFD) and the simple centralized decoding (SCD) are utilized, respectively, and for the downlink, the maximal ratio (MR) precoding and fractional power control (FPC) are adopted. Moreover, the optimal LSFD coefficients that maximize the uplink SE is presented. Afterwards, for further enhancement of SEs, a novel optimization scheme is presented, which optimizes the passive beamforming (PB) of the STAR-RIS to minimize the normalized mean square error (NMSE) of the aggregated channel estimation. The simulation results reveal that the STAR-RIS-aided CF-mMIMO system achieves superior uplink and downlink performance compared to both the RIS-aided CF-mMIMO system and the conventional CF-mMIMO system without RIS over aging channel. Furthermore, the results show that the PB optimization can significantly reduce the NMSE of channel estimation, thereby improving the estimation accuracy and SEs under channel aging.

Blockchain-based steganography enables data hiding via encoding the covert data into a specific blockchain transaction field. However, previous works focus on the specific field-embedding methods while lacking a consideration on required field-generation embedding. In this paper, we propose a generic blockchain-based steganography framework (GBSF). The sender generates the required fields such as amount and fees, where the additional covert data is embedded to enhance the channel capacity. Based on GBSF, we design a reversible generative adversarial network (R-GAN) that utilizes the generative adversarial network with a reversible generator to generate the required fields and encode additional covert data into the input noise of the reversible generator. We then explore the performance flaw of R-GAN. To further improve the performance, we propose R-GAN withCounter-intuitive data preprocessing andCustom activation functions, namelyCCR-GAN. The counter-intuitive data preprocessing (CIDP) mechanism is used to reduce decoding errors in covert data, while it incurs gradient explosion for model convergence. The custom activation function named ClipSigmoid is devised to overcome the problem. Theoretical justification for CIDP and ClipSigmoid is also provided. We also develop a mechanism named T2C, which balances capacity and concealment. We conduct experiments using the transaction amount of the Bitcoin mainnet as the required field to verify the feasibility. We then apply the proposed schemes to other transaction fields and blockchains to demonstrate the scalability. Finally, we evaluate capacity and concealment for various blockchains and transaction fields and explore the trade-off between capacity and concealment. Experimental results demonstrate that R-GAN and CCR-GAN are able to enhance the channel capacity effectively and outperform state-of-the-art works.

As a paradigm for encouraging users to contribute data spontaneously, mobile crowdsensing (MCS) has received considerable attention recently. It is crucial to evaluate the truthfulness of MCS data by proper truth discovery mechanisms. Although recent truth discovery schemes can determine truthful information, they either provide limited privacy preservation or have heavy computation and communication overheads. Moreover, most of them are not resilient to malicious faults and active attacks. To tackle the above problems, we propose two fault-tolerant and privacy-preserving truth discovery solutions. Our first scheme is mainly used for scenarios with a relatively stable number of users, where participants do not frequently join or leaves. Integrating ring signature with the perturbation technique, we design an anonymous and privacy-preserving truth discovery scheme, namely RsAnonTD, which can achieve privacy preservation and resist active attacks. To address the challenge with dynamically changed workers, we devise a multi-client inner product functional encryption scheme with a lightweight zero-knowledge proof protocol (namely McFeKDeTD) for defending against active attacks. The security analysis shows that both schemes can preserve the privacy of sensory data, weights, and estimated truths while resisting active attacks, thereby guaranteeing fault tolerance. Extensive experiments demonstrate that our designs achieve superior performance than other schemes in terms of accuracy, convergence speed, and system overheads. For example, compared with the state-of-the-art approach RPTD-II, which has a security level comparable to ours, our proposed schemes, RsAnonTD and McFeKDeTD, reduce the computational overheads approximately by 98% and 69%, respectively.

With the rapid advancement of 6G, identity authentication has become increasingly critical for ensuring wireless security. The lightweight and keyless Physical Layer Authentication (PLA) is regarded as an instrumental security measure in addition to traditional cryptography-based authentication methods. However, existing PLA schemes often struggle to adapt to dynamic radio environments. To overcome this limitation, we propose the Adaptive PLA with Channel Extrapolation and Generative AI (APEG), designed to enhance authentication robustness in dynamic scenarios. Leveraging Generative AI (GAI), the framework adaptively generates Channel State Information (CSI) fingerprints, thereby improving the precision of identity verification. To refine CSI fingerprint generation, we propose the Collaborator-Cleaned Masked Denoising Diffusion Probabilistic Model (CCMDM), which incorporates collaborator-provided fingerprints as conditional inputs for channel extrapolation. Additionally, we develop the Cross-Attention Denoising Diffusion Probabilistic Model (CADM), employing a cross-attention mechanism to align multi-scale channel fingerprint features, further enhancing generation accuracy. Simulation results demonstrate the superiority of the APEG framework over existing time-sequence-based PLA schemes in authentication performance. Notably, CCMDM exhibits a significant advantage in convergence speed, while CADM, compared with model-free, time-series, and VAE-based methods, achieves superior accuracy in CSI fingerprint generation.

Smart contracts play a pivotal role in blockchain ecosystems, and fuzzing remains a critical approach to securing them. However, existing smart contract fuzzers often optimize either seed generation or mutation scheduling in isolation and rely on narrow, fragmented feedback signals, leaving multi-transaction reasoning and stagnation recovery under-explored. In this work, we propose aLarge Language Models(LLMs)-based Multi-feedback Smart Contract Fuzzing framework (LLAMA). Key components of the proposed LLAMA include: (i) a hierarchical prompting strategy that guides LLMs to generate structurally valid, context-aware multi-transaction initial seeds, together with a lightweight pre-fuzzing phase that validates and prioritizes high-potential LLM-generated candidates; (ii) a multi-feedback-guided evolutionary optimization module that jointly optimizes seed selection and mutation scheduling by a group of constraints for driving an LLM-bootstrapped bandit scheduler. (iii) an LLM-guided hybrid fuzzing module that integrates evolutionary fuzzing with a dual-channel recovery mechanism, which concurrently employs asynchronous coverage-stagnation- based LLM reseeding and selective symbolic execution to resolve complex path constraints. Our extensive experiments demonstrate that LLAMA outperforms state-of-the-art fuzzers in both coverage and vulnerability detection. Specifically, it achieves 92% instruction coverage on small contracts and 81% on large contracts, while detecting 132 out of 148 known vulnerabilities across diverse categories. Ablation studies further evidence that the proposed multi-feedback and hybrid recovery strategies have strong impact on LLAMA’s performance. The results explain LLAMA’s effectiveness, adaptability, and practicality in complex smart contract scenarios.

Recommendation systems based on graph neural networks (GNNs) have emerged as a promising paradigm due to their ability to capture high-order interactions between users and items. However, in federated scenarios, this advantage is compromised, as each user can access only a first-order subgraph composed of its directly interacted items. To address this issue, most existing solutions introduce a trusted server to assist users in expanding their local subgraphs. However, the server in reality is often untrusted and may deviate from the protocol for its own improper benefit. Furthermore, these solutions primarily focus on the privacy of items while neglecting the privacy of potential relationships between users. To this end, we propose Garland, a GNN-based federated recommendation scheme with malicious security. Garland departs from existing work by ensuring both item and relationship privacy while supporting integrity checks to defend against malicious servers. Specifically, we employ a trending cryptographic primitive of secret-shared shuffle to expand subgraphs in a privacy-preserving and verifiable manner. We also design a pre-shuffle triple-salt encryption mechanism and a post-shuffle user-governed expansion mechanism to reduce communication costs and achieve secure distribution of neighbor information, respectively. Moreover, we develop a secret-shared aggregation mechanism to enable privacy-preserving and verifiable federated training. Theoretical analysis demonstrates the privacy and integrity of Garland. Extensive experimental evaluations on four datasets show that Garland outperforms state-of-the-art solutions.

Blockchain plays a crucial role in ensuring the security and integrity of decentralized systems, with the proof-of-work (PoW) mechanism being fundamental for achieving distributed consensus. As PoW blockchains see broader adoption, an increasingly diverse set of miners with varying computing capabilities participate in the network. In this paper, we consider the PoWblockchain mining, where the miners are associated with resource uncertainties. To characterize the uncertainty computing resources at different mining participants, we establish an ambiguous set representing uncertainty of resource distributions. Then, the networked mining is formulated as a non-cooperative game, where distributionally robust performance is calculated for each individual miner to tackle the resource uncertainties. We prove the existence of the equilibrium of the distributionally robust mining game. To derive the equilibrium, we propose the conditional value-at-risk (CVaR)-based reinterpretation of the best response of each miner. We then solve the individual strategy with alternating optimization, which facilitates the iteration among miners towards the game equilibrium. Furthermore, we consider the case that the ambiguity of resource distribution reduces to Gaussian distribution and the case that another uncertainties vanish, and then characterize the properties of the equilibrium therein along with a distributed algorithm to achieve the equilibrium. Simulation results show that the proposed approaches effectively converge to the equilibrium, and effectively tackle the uncertainties in blockchain mining to achieve a robust performance guarantee.

Vertical Split Federated Learning (VSFL) allows participants to collaboratively train a better model with different features vertically partitioned in the same sample space, where the model is divided into bottom model and top model by the cut layer, trained by passive and active participants respectively. However, in the process, the labels owned by the active participant will still be inferred or stolen by curious or malicious passive participants. In this paper, we propose Casper, a causality-inspired defense mechanism with a confounder against label inference attacks in VSFL. Casper first analyzes the feasibility of optimizing the training process in VSFL at the intervention level from a causal perspective. It then introduces a confounder consisting of cut layer output reconstruction and label obfuscation to disrupt the direct causality between cut layer outputs and labels. Additionally, we integrate selective discrepancy training to further ensure model utility by strategically balancing training between active and passive participants. Extensive experiments conducted on four datasets across different tasks demonstrate that Casper effectively preserves label privacy while maintaining model performance, significantly outperforming current advanced defending methods in VSFL.

Wireless sensing is recognized as a promising technology for next-generation wireless networks, utilizing signals from devices such as Wi-Fi to detect and interpret human information, including movement status and sleep quality. However, the broadcast nature of wireless signals poses significant privacy risks, as unauthorized users may intercept these signals, leading to potential privacy breaches. Given the sensitive personal information embedded in CSI data and the limitations of encryption at the transmission end, conventional privacy protection measures are inadequate. Thus, developing physical layer-based privacy protection technologies for wireless sensing is urgently needed. In this paper, we consider a wireless sensing system model addressing privacy leakage issues and characterize wireless sensing performance as a classification problem. We propose a novel multi-antenna signal processing-based privacy protection strategy. To illustrate the fundamental tradeoff between sensing and privacy protection, we model the wireless sensing process as a communication task based on non-cooperative joint source-channel coding and introduce the concept of a sensing rate region. Our main contribution is the characterization of sensing and privacy protection performance at two key points within the sensing rate region:POS, indicating the minimum achievable sensing rate of an illegitimate receiver constrained by the maximum sensing rate of a legitimate receiver, andPOPP, indicating the maximum sensing rate of a legitimate receiver constrained by the minimum sensing rate of an illegitimate receiver. Based on our analysis, we provide strategies to establish achievable boundaries betweenPOSandPOPP. Moreover, we define the secure sensing rateRPP, indicating the privacy protection performance of the system. Within this framework, we examine several illustrative examples, validated through numerical simulations.

Malicious jamming presents a pervasive threat to the secure communications, where the challenge becomes increasingly severe due to the growing capability of the jammer allowing the adaptation to legitimate transmissions. This paper investigates the jamming mitigation by leveraging an active reconfigurable intelligent surface (ARIS), where the channel uncertainties are particularly addressed for robust anti-jamming design. Towards this issue, we adopt the Stackelberg game formulation to model the strategic interaction between the legitimate side and the adversary, acting as the leader and follower, respectively. We prove the existence of the game equilibrium and adopt the backward induction method for equilibrium analysis. We first derive the optimal jamming policy as the follower’s best response, which is then incorporated into the legitimate-side optimization for robust anti-jamming design. We address the uncertainty issue and reformulate the legitimate-side problem by exploiting the error bounds to combat the worst-case jamming attacks. The problem is decomposed within a block successive upper bound minimization (BSUM) framework to tackle the power allocation, transceiving beamforming, and active reflection, respectively, which are iterated towards the robust jamming mitigation scheme. Simulation results are provided to demonstrate the effectiveness of the proposed scheme in protecting the legitimate transmissions under uncertainties, and the superior performance in terms of jamming mitigation as compared with the baselines.

The increasing saturation of terrestrial resources has driven the exploration of low-altitude applications such as air taxis. Low altitude wireless networks (LAWNs) serve as the foundation for these applications, and integrated sensing and communication (ISAC) constitutes one of the core technologies within LAWNs. However, the open nature of low-altitude airspace makes LAWNs vulnerable to malicious channel access attacks, which degrade the ISAC performance. Therefore, this paper develops a game-based framework to mitigate the influence of the attacks on LAWNs. Concretely, we first derive expressions of communication data’s signal-to-interference-plus-noise ratio and the age of information of sensing data under attack conditions, which serve as quality of service metrics. Then, we formulate the ISAC performance optimization problem as a Stackelberg game, where the attacker acts as the leader, and the legitimate drone and the ground ISAC base station act as second and first followers, respectively. On this basis, we design a backward induction algorithm that achieves the Stackelberg equilibrium while maximizing the utilities of all participants, thereby mitigating the attack-induced degradation of ISAC performance in LAWNs. We further prove the existence of the equilibrium. Simulation results show that the proposed algorithm outperforms existing baselines and a static Nash equilibrium benchmark, ensuring that LAWNs can provide reliable service for low-altitude applications.

Passive eavesdropping compromises confidentiality in wireless networks, especially in resource-constrained environments where heavyweight cryptography is impractical. Physical layer security (PLS) exploits channel randomness and spatial selectivity to confine information to an intended receiver with modest overhead. However, typical PLS techniques, such as beamforming, artificial noise, and reconfigurable intelligent surfaces, often require additional active power or specialized deployment and rely on precise time synchronization and perfect CSI estimation, which limits their practicality. Meanwhile, the role of ambient backscatter devices (AmBDs) in potentially strengthening the legitimate channel while limiting eavesdroppers in generalized wireless network settings has not been fully investigated. To this end, we propose AmbShield, an AmBD-assisted PLS scheme that leverages naturally distributed AmBDs to simultaneously strengthen the legitimate channel and degrade eavesdroppers' reception without requiring extra transmit power and with minimal deployment overhead. In AmbShield, AmBDs are exploited as friendly jammers that randomly backscatter to create interference at eavesdroppers, and as passive relays that backscatter the desired signal to enhance the capacity of legitimate devices. We further develop a unified analytical framework that analyzes the exact probability density function (PDF) and cumulative distribution function (CDF) of legitimate and eavesdropper signal-to-interference-noise ratio (SINR), a closed-form secrecy outage probability (SOP), its high-SNR asymptote, and a secrecy diversity order (SDO). The analysis provides clear design guidelines on various practical system parameters to minimize SOP. Extensive experiments that include Monte Carlo simulations, theoretical derivations, and high-SNR asymptotic analysis demonstrate the security gains of AmbShield across diverse system parameters under imperfect synchronization and CSI estimation.

Future 6G-enabled industrial systems will rely on distributed sensing and control over communication networks to manage concurrent processes, collaboratively achieving system-level operational objectives. However, various physical constraints, including excessive communication delays, complex interprocess dependencies, and dynamic system objectives, inevitably cause deteriorated operational outcomes compared to ideal conditions. To minimize this operational loss, we propose a goal-oriented digital twin (GDT) framework that overcomes these physical constraints through system orchestration in the virtual domain for dynamic objective fulfillment. Based on operational goals, the proposed GDT selectively integrates distributed sensing information into system digital twins, which then map system-level objectives into executable control tasks for individual devices. Specifically, by continuously evaluating the goal relevance of sensing data from individual devices, distributed observations are selected and prioritized, enabling control-aware communication resource allocation that balances control performance and communication efficiency. Moreover, delay-compensated control commands are accurately derived within the GDT framework, where the sensed temporal synchrony and interprocess dependencies are intentionally considered for coordinated task execution across distributed devices. Through this cohesive joint sensing and control design in the virtual domain, system-level objectives are fulfilled with minimized operational loss. Extensive simulations validate that GDT significantly improves control accuracy and resource efficiency in large-scale industrial systems.

Point clouds have gained prominence across numerous applications due to their ability to accurately represent 3D objects and scenes. However, efficiently compressing unstructured, high-precision point cloud data remains a significant challenge. In this paper, we propose NeRC ${}^{\textbf {3}}$ , a novel point cloud compression framework that leverages implicit neural representations (INRs) to encode both geometry and attributes of dense point clouds. Our approach employs two coordinate-based neural networks: one maps spatial coordinates to voxel occupancy, while the other maps occupied voxels to their attributes, thereby implicitly representing the geometry and attributes of a voxelized point cloud. The encoder quantizes and compresses network parameters alongside auxiliary information required for reconstruction, while the decoder reconstructs the original point cloud by inputting voxel coordinates into the neural networks. Furthermore, we extend our method to dynamic point cloud compression through techniques that reduce temporal redundancy, including a 4D spatio-temporal representation termed 4D-NeRC ${}^{\textbf {3}}$ . Experimental results validate the effectiveness of our approach: For static point clouds, NeRC ${}^{\textbf {3}}$ outperforms octree-based G-PCC standard and existing INR-based methods. For dynamic point clouds, 4D-NeRC ${}^{\textbf {3}}$ achieves superior geometry compression performance compared to the latest G-PCC and V-PCC standards, while matching state-of-the-art learning-based methods. It also demonstrates competitive performance in joint geometry and attribute compression.

Low-altitude economy networking (LAENet) aims to deploy various aerial vehicles to support diverse services, where data collection from edge devices via unmanned aerial vehicles (UAVs) is a critical task. The key challenge lies in jointly optimizing energy consumption and data freshness in spectrum-constrained and eavesdropping-prone low-altitude environments during the data collection process. Although deep reinforcement learning (DRL) has become a viable solution for UAV-assisted data collection, the RL agent still has limited ability to obtain and utilize informative feedback from complex low-altitude environments. In this paper, we propose a large language model (LLM)-enhanced DRL framework for secure data collection in the LAENet, where we leverage an LLM to process environmental feedback for the RL agent. Specifically, we employ the LLM as (i) a state processor to transform basic environmental observations into task-aligned representations, (ii) a reward designer to generate enriched reward signals that guide the agent's actions toward the optimization objective, and (iii) a simulator to construct a virtual LAENet environment for evaluating enhanced state-reward pairs before policy training. Theoretical analysis and numerical results demonstrate that the proposed LLM-enhanced DRL framework achieves faster convergence, improved training stability, and superior performance compared with state-of-the-art baselines.

In mobile edge computing (MEC), computation offloading serves as an effective solution to bridge the gap between the stringent latency requirements of computational tasks and the limited processing capabilities of terminal devices (TDs). However, complex inter-task dependencies, dynamic network conditions, and the decentralized architecture of MEC systems pose significant challenges to efficient and adaptive task offloading. To address these challenges, this paper investigates dependency-aware task offloading and resource optimization in MEC environments. First, we propose a task feature extraction method based on dependency-aware graph neural networks (FEDG), which captures the hierarchical structure and varying importance of subtask dependencies by adaptively learning the aggregation weights of predecessor nodes and edges. Then, to address the joint dependency-aware task offloading and resource allocation problem under partial observability in MEC networks, we design a Dependency-aware Graph-based Multi-Agent deep reinforcement learning (DGMA) algorithm. DGMA integrates adaptive prioritized experience replay and correlation-based selective parameter sharing to improve learning efficiency and accelerate convergence in multi-agent environments. Extensive simulations demonstrate that DGMA achieves superior performance in terms of delay, energy consumption, offloading utility, and deadline violation rate.

Vehicular metaverses enable immersive digital experiences through seamless Vehicle Twin (VT) services. As vehicles move, VT service instances must migrate between RoadSide Units (RSUs) to sustain low-latency interactions. However, RSUs face significant challenges from dynamic workload fluctuations and uneven geographical distribution. These limitations often result in service degradation during peak demand periods. Unmanned Aerial Vehicles (UAVs) offer promising solutions to augment fixed infrastructure capacity. Nevertheless, their energy constraints and trajectory optimization create additional complexity for resource management. To address these challenges, we develop a novel framework integrating workload forecasting with coordinated decision-making for VT migration and UAV routing. We first design a long short-term memory-based workload prediction model. This model predicts workload patterns by combining spatial feature extraction with temporal dependency modeling. We enhance the prediction capability through noise-augmented training to improve robustness. Then, we formulate the VT migration and UAV routing optimization as a markov decision process, which captures the sequential nature of decision-making. Finally, we propose a hierarchical control multi-agent deep reinforcement learning algorithm where the upper-layer controller uses multi-agent proximal policy optimization for collaborative decision-making, and the lower-layer controller handles VT migration and UAV routing execution. Simulation results show that the proposed approach reduces average latency by 25.70% and validation loss by 63.70% for workload prediction compared to baseline methods.

The Internet of Vehicles (IoV) is emerging as a pivotal technology for enhancing traffic management and safety. Its rapid development demands solutions for enhanced communication efficiency and reduced latency. However, traditional centralized networks struggle to meet these demands, prompting the exploration of decentralized solutions such as blockchain. Addressing blockchain's scalability challenges posed by the growing number of nodes and transactions calls for innovative solutions, among which sharding stands out as a pivotal approach to significantly enhance blockchain throughput. However, existing schemes still face challenges related to a) the impact of vehicle mobility on blockchain consensus, especially for cross-shard transaction; and b) the strict requirements of low latency consensus in a highly dynamic network. In this paper, we propose a DAG (Directed Acyclic Graph) consensus leveraging Robust Dynamic Sharding and Tree-broadcasting (DRDST) to address these challenges. Specifically, we first develop a standard for evaluating the network stability of nodes, combined with the nodes' trust values, to propose a novel robust sharding model that is solved through the design of the Genetic Sharding Algorithm (GSA). Then, we optimize the broadcast latency of the whole sharded network by improving the tree-broadcasting to minimize the maximum broadcast latency within each shard. On this basis, we also design a DAG consensus scheme based on an improved hashgraph protocol, which can efficiently handle crossshard transactions. Finally, the simulation proves the proposed scheme is superior to the comparison schemes in latency, throughput, consensus success rate, and node traffic load.

The rapid development of the low-altitude economy (LAE) has accelerated the deployment of cargo unmanned aerial vehicles (UAVs) for intelligent logistics and delivery services. However, large-scale UAV operations still face multiple practical challenges, including unstable communication connectivity, limited onboard battery energy, and strict customer time-window constraints. To address these issues, this paper investigates the trajectory and task scheduling optimization problem for multi-UAV cooperative cargo pick-up under joint communication, energy, and time-window constraints. We develop a collision-aware cooperative multi-UAV optimization algorithm (CACMO) that integrates a Dueling Deep Q-Network (D3QN) for communication-aware trajectory learning with a simulated annealing (SA) based global task-sequence planner and an explicit inter-UAV conflict-resolution mechanism. The D3QN module enables adaptive trajectory generation in unknown and time-varying radio environments without requiring an a priori radio map, maintaining stable connectivity while reducing flight cost, whereas the SA module determines efficient task orders and enforces safe coordination among multiple UAVs through collision-aware refinement. Simulation results demonstrate that the proposed CACMO algorithm framework achieves an optimal balance between task completion time (1,719 seconds) and user satisfaction (score of 0.9969) under typical operating conditions, delivering a 70–75% reduction in total weighted cost compared to representative baseline methods. Crucially, this substantial improvement is achieved while explicitly enforcing multi-UAV collision avoidance-a critical constraint absent in most baseline methods. The framework maintains zero communication outage and guarantees safe inter-UAV separation throughout the mission while satisfying all energy and time window constraints in realistic urban environments, confirming its robustness and scalability for cooperative multi-UAV logistics operations within the LAE.

In this paper, we propose a novel generative artificial intelligence (GAI)-aided approach to address the quality of experience (QoE)-aware resource allocation for reconfigurable intelligent surface (RIS)-assisted digital twin (DT) interactions with uncertain evolutions. In the considered system, mobile users interact with a DT model, referring to the high-fidelity and interactive virtual counterpart of a physical entity, hosted by a DT server deployed on a wireless base station via the assistance of an RIS, for gaining DT services, such as real-time monitoring and predictive analytics. Noted that DT interactions involve round-trip communications with both uplink and downlink, and concern not only objective performance but also subjective experience. As such, we formulate an optimization problem for RIS-assisted DT interactions, aiming to maximize the sum of all mobile users' mixed objective and subjective QoE, by jointly determining the phase shift marix, receive/transmit beamforming matrices, feedback signal rendering resolution and computing resource configuration. Further taking into account the DT model's uncertain evolutions and the resulted variations of the DT scene that mobile users engage in, we extend the resource allocation problem to a series of scene-specific ones. To obtain a generalized approach with low complexity, avoiding to re-solve each scene-specific problem whenever the engaged DT scene changes, we develop a GAI-aided approach, called prompt-guided decision transformer integrated with zero-forcing optimization (PG-ZFO). Specifically, in PG-ZFO, we first reformulate each scene-specific problem into a Markov decision process (MDP). Then, we design a “decision-making trajectory” based prompt to capture the scene-specific information and extend the traditional decision transformer to a prompt-guided decision transformer with strong generalization. On top of that, a zero-forcing (ZF)-based optimization algorithm is integrated to help derive high-dimensional decisions, i.e., beamforming matrix, along with the offline training and online execution of PG-ZFO. Simulations show the effectiveness of the proposed approach, and demonstrate its superiority over counterparts, i.e., rigid optimization method and decision transformer without prompt.

Aiming to provide high-fidelity and real-time virtual replicas, a digital twin (DT) model must be dynamically updated to precisely characterize the evolution of physical objects. Unlike the existing work, this paper studies a novel edge-cloud collaborative DT update framework with adaptive model splitting and reliable crowdsourcing under uncertain data distortions. Specifically, we consider that a global DT model can be split into arbitrary subsets of its elementary components (DT units), re-forming disjoint partial-DTs. Each partial-DT is constructed on distributed edge servers (ESs) by model training using the locally collected feature data. To enhance the system reliability, being more robust against uncertain data distortions that widely occur in practice, we further improve partial-DT constructions via crowdsourcing. In other words, each partial-DT is simultaneously trained by multiple ESs, i.e., an ES crowd, with one coordinator ES intermediately aggregating all models from participating ESs into a unified one. Then, the cloud collects and integrates partial-DTs from ES crowds to update the global DT. We formulate an online joint optimization problem to adaptively determine partial-DT splitting and ES crowdsourcing across different DT evolution periods or frames, with the objective of maximizing the long-term physical-virtual mapping accuracy. To this end, we first study a simplified short-term problem in each frame, modeled as a Bayesian coalition formation game (BCFG). We then develop an uncertainty-aware crowd formation algorithm based on a particularly established believe function to solve the BCFG for short-term optimal partial-DT assignment and coordinator ES selection, given any partial-DT splitting decisions. Moreover, we modify the BCFG to accommodate dynamic settings and design a deep reinforcement learning-based algorithm integrated with this modified BCFG, called DBC. The DBC algorithm extends the short-term solution to a long-term one, which jointly and dynamically optimizes partial-DT splitting and ES crowdsourcing, thereby addressing the original problem. Simulations show the effectiveness of the introduced dynamic DT update framework, and demonstrate the superiority of the proposed DBC algorithm over counterparts in terms of increasing the average DT update accuracy while reducing the associated costs.

Supported by space-air-ground integrated networks (SAGIN), Internet of Remote Things (IoRT) is regarded as a cornerstone for realizing global connectivity in 6 G networks. The integration of high-altitude platforms (HAPs) and unmanned aerial vehicles (UAVs), offering both wide coverage and agile data access, becomes a promising paradigm for IoRT data collection. However, sustaining reliable and efficient transmission is challenged by the mobility and constrained onboard energy of HAPs and UAVs, as well as atmospheric fading effects. To address these issues, we propose a green and efficient HAP-UAV collaborative design for IoRT data collection, which jointly considers both transmission performance and energy consumption. Firstly, we introduce a novel metric, Overall Energy Efficiency (OEE), to quantify the balance between cooperative transmission performance and the total energy cost under dynamic trajectory planning. Secondly, we formulate a joint optimization problem that simultaneously optimizes UAV/HAP trajectories, UAV power control, HAP selection, and bandwidth allocation. Thirdly, to address the formulated non-convex fractional problem, we develop an energy efficiency maximization strategy based on the successive convex approximation technique. Extensive simulation results demonstrate that the proposed strategy achieves significant gains in OEE, achieving superior trade-offs between energy consumption and transmission performance in HAP-UAV-assisted IoRT networks.

Efficient and reliable neighbor discovery is critical for UAV networks equipped with directional antennas, particularly in dynamic and energy-constrained environments. We present a novel optimization framework that jointly minimizes delay and power consumption using the power-delay product as the optimization metric. The framework is formulated for both synchronous and asynchronous schemes, leveraging upper-bound metrics and a convex-concave procedure to achieve tractable convex formulations. Simulation results validate the theoretical models and show significant improvements over baseline methods. We also conducted real-world experiments, where our method reduced power-delay product by 11% compared to the baseline, though the dual-sector hardware configuration limited the achievable gains. This work provides a comprehensive solution for UAV neighbor discovery, with high potential for scalability in more complex and dynamic environments.

Semantic communication (SemCom), as a novel paradigm for future communication systems, has recently attracted much attention due to its superiority in communication efficiency. However, similar to traditional communication, it also suffers from eavesdropping threats. Intelligent eavesdroppers could launch advanced semantic analysis techniques to infer secret semantic information. Therefore, some researchers have designed Semantic Steganography Communication (SemSteCom) schemes to confuse semantic eavesdroppers. However, the state-of-the-art SemSteCom schemes for image transmission rely on the pre-selected cover image, which limits the generalization. To address this issue, we propose a Generative Diffusion Model-based Coverless Semantic Steganography Communication (SemSteDiff) scheme to hide secret images into generated stego images. The semantic related private and public keys enable legitimate receiver to decode secret images correctly while the eavesdropper without the completely correct key-pairs fail to obtain them. Simulation results demonstrate the effectiveness of the plug-and-play design in different Joint Source-Channel Coding (JSCC) frameworks. Results under different eavesdropping settings show that, when Signal-to-Noise Ratio (SNR) = 0 dB, the peak signal-to-noise ratio (PSNR) of the legitimate receiver is 4.14 dB higher than that of the eavesdropper.

Deep Neural Networks (DNNs) are increasingly adopted across various industries, driving the demand for deploying their capabilities on mobile devices. However, current mobile inference frameworks often rely on a single processor to execute each model inference, limiting hardware utilization and leading to suboptimal performance and energy efficiency. Expanding DNN accessibility on mobile platforms requires more adaptive and resource-efficient solutions to meet increasing computational demands without compromising device functionality. Nevertheless, performing parallel inference of multiple DNNs on heterogeneous processors remains a significant challenge. Existing studies have explored partitioning DNN operations into subgraphs to enable parallel execution across heterogeneous processors. However, these approaches typically generate excessive subgraphs based solely on hardware compatibility, increasing scheduling complexity and memory management overhead. To address these limitations, we propose the Advanced Multi-DNN Model Scheduling (ADMS) strategy that optimizes multi-DNN inference across heterogeneous processors on mobile devices. ADMS constructs an offline subgraph partitioning strategy that considers both hardware support for operations and scheduling granularity. It also employs a processor-state-aware scheduling algorithm to dynamically balance workloads based on real-time system conditions. This ensures efficient workload distribution and maximizes the utilization of available processors. Experimental results demonstrate that, compared to vanilla inference frameworks, ADMS achieves a 4.04× reduction in multi-DNN inference latency.

The rapid growth of the low-altitude economy has driven the widespread adoption of unmanned aerial vehicles (UAVs). This growing deployment presents new challenges for UAV trajectory planning in complex urban environments. However, existing studies often overlook key factors, such as urban airspace constraints and economic efficiency, which are essential in low-altitude economy contexts. Deep reinforcement learning (DRL) is regarded as a promising solution to these issues, while its practical adoption remains limited by low learning efficiency. To overcome this limitation, we propose a novel UAV trajectory planning algorithm that integrates DRL with the large language model (LLM) reasoning to enable safe, compliant, and economically viable trajectory planning. Specifically, we model the trajectory planning task as a partially observable Markov decision process, explicitly incorporating obstacle avoidance, regulation awareness, and energy constraints. We design a hybrid optimization algorithm based on the soft actor-critic algorithm and LLM reasoning to enable adaptive decision-making in uncertain and dynamic environments. Experimental results demonstrate that our algorithm achieves the best overall performance, with the highest data collection rate (99.50%), almost zero collision avoidance rate and regulation violation rate, a successful landing rate of nearly 100%, and the lowest energy consumption rate (76.95%). These results validate the effectiveness of our algorithm in addressing UAV trajectory planning key challenges under constraints of the low-altitude economy networking.

Unmanned aerial vehicle (UAV)-assisted ground robot networks (UGRNets) are playing an increasingly critical role in a wide range of time-sensitive and mission-critical applications, such as environmental monitoring, infrastructure inspection, and emergency response. UGRNets require not only low-latency communication but also high spatial awareness to ensure effective coordination and decision-making. This paper proposes a unified spatiotemporal framework that evaluates and enhances the quality of updated information in UGRNets from both temporal and spatial dimensions. On the temporal side, we develop a martingale-theory-based prediction method for the delay violation probability bound (DVPB), coupled with a novel joint decay rate model to accurately characterize latency violations in heterogeneous multi-hop communication UGRNets. On the spatial side, we introduce the use of Wasserstein distance to quantify and improve the spatial completeness of robotic coverage. By integrating these metrics, we formulate a spatiotemporal optimization problem that jointly minimizes DVPB and maximizes spatial completeness, enabling robotic agents to adapt their information collection strategies accordingly. Numerical results demonstrate that the proposed framework significantly improves information timeliness and spatial completeness in heterogeneous and dynamic UGRNets scenarios, thereby providing practical insights for real-world deployment.

Enhanced by inter-satellite links and satellite direct-to-device capabilities, satellite networks can offer low-latency communication globally. However, limited spectrum resources and the capacity bounds of the Shannon's information theory pose fundamental challenges for supporting bandwidth-intensive multimedia services. Semantic communication (SemCom) offers a promising solution by transmitting compressed semantic representations instead of raw data, thereby alleviating bandwidth pressure. However, it also introduces SemCom-related constraints that render conventional schemes such as contact graph routing inapplicable. To overcome this challenge, we investigate SemCom-compliant path selection and formulate it as a non-NP hard mixed-integer linear programming problem. To address the problem, we develop a graph-based scheme that exploits the special structure of the solution space, the sparsity of SemCom-capable satellites, and the property of Dijkstra's algorithm, thus achieving optimal solutions with polynomial-time complexity. Simulation results on the Starlink constellation confirm that the proposed scheme facilitates SemCom with negligible computational overhead and significant bandwidth reduction. While the bandwidth reduction comes at the cost of increased delay and path hops, these effects are shown to be mitigatable through higher SemCom deployment in a satellite network or by enabling semantic processing at the user side.

This paper proposes a graph neural network (GNN)-enabled coordinated beamforming design, termed HSTGNN, for high speed railway (HSR) communication systems, where a high-speed train (HST) and low-speed users (LUs) coexist in multi-cell scenarios. Two transmission schemes with the goal of maximizing quality-of-service (QoS)-constrained sum rate and rate of the HST are formulated and then reformulated using a hybrid maximum ratio transmission and zero-forcing strategy. The HSR communication system is abstracted into a heterogeneous graph, and HSTGNN consists of complex heterogeneous graph attention layers and fully-connected layers. To meet QoS requirements and power budget constraints, we employ constraint-based penalty terms and a numerical scaling operation. HSTGNN is trained via unsupervised learning to solve the two schemes in a unified framework. Numerical results demonstrate that HSTGNN achieves millisecond-level inference speed with an average optimality gap of only 4% relative to traditional optimization algorithm across various scenarios. Moreover, HSTGNN exhibits strong scalability to unseen configurations of both cells and LUs.

With the exponential growth of smart devices connected to wireless networks, data production is increasing rapidly, requiring machine learning (ML) techniques to unlock its value. However, the centralized ML paradigm raises concerns over communication overhead and privacy. Federated learning (FL) offers an alternative at the network edge, but practical deployment in wireless networks remains challenging. This paper proposes a lightweight FL (LTFL) framework integrating wireless transmission power control, model pruning, and gradient quantization. We derive a closed-form expression of the FL convergence gap, considering transmission error, model pruning error, and gradient quantization error. Based on these insights, we formulate an optimization problem to minimize the convergence gap while meeting delay and energy constraints. To solve the non-convex problem efficiently, we derive closed-form solutions for the optimal model pruning ratio and gradient quantization level, and employ Bayesian optimization for transmission power control. Extensive experiments on real-world datasets show that LTFL outperforms state-of-the-art schemes.

Low Earth orbit (LEO) satellites can be used to assist maritime wireless communications for wide-area data transmission. However, the extensive coverage of LEO satellites, combined with the openness of channels, can cause the communication process to suffer from security risks. This paper presents a LEO satellite-maritime communication system assisted by low-altitude unmanned aerial vehicle (UAV) friendly-jamming to ensure data security at the physical layer. Since such a system requires balancing the conflicting performance metrics of secrecy rate and energy consumption of the UAV to meet evolving scenario demands, we formulate a secure satellite-maritime communication multi-objective optimization problem (SSMCMOP). In order to solve the dynamic and long-term optimization problem, we reformulate it into a Markov decision process. We then propose a transformer-enhanced soft actor-critic (TransSAC) algorithm, which is a generative artificial intelligence-enabled deep reinforcement learning approach to solve the reformulated problem, thus capturing strong temporal correlations and diversely exploring weights. Simulation results demonstrate that the TransSAC algorithm outperforms comparative approaches and algorithms, maximizing the secrecy rate while effectively minimizing the energy consumption of the UAV. Moreover, the results identify more suitable constraints for the system.

User devices (UDs) with non-independent and identically distributed (non-IID) data will worsen accuracy performance of the global model in federated learning (FL). Therefore, the implementation of diffusion strategies in machine learning (ML) models can enhance the effectiveness of federated learning with non-IID data. However, in a device-to-device (D2D) wireless federated learning (WFL) system, limited wireless resources and severe wireless channel interference become the important bottleneck to restrict the diffusion performance and model aggregation so as the global model of WFL with non-IID suffers from the weight divergence challenge. Thus, we propose a novel joint over-the-air computation (OAC) aggregation and diffusion framework by using a graph neural network (GNN) for WFL, termed an OAC-GNN-Dif framework. By integrating the OAC with message passing neural network (MPNN) of GNN, we further develop the OAC-MPNN-Dif algorithm based on the OAC-GNN-Dif framework. To further reduce communication costs, we designed an OAC message recurrent neural network (OAC-MPRNN-Dif) algorithm, where each UD propagates local models via D2D communications to refresh the graph embedding in the current frame based on the graph feature extraction and localization state of the previous frame to reduce communication costs. Additionally, we introduce dynamic time-varying MPNN for federated diffusion within evolving D2D network topologies. The experimental results indicate that our approach significantly performs well in communication overhead, with a 30%-60% decreasing in wireless resources overhead and 1.2-3.5 times decreasing in the number of model transfers compared to the FedDif methods. Moreover, our approach also improves the global model test accuracy, which is about 2.7% higher than the existing communication diffusion FL with non-IID characteristics.

Low-altitude wireless networks (LAWNs) have been envisioned as flexible and transformative platforms for enabling delay-sensitive control applications in Internet of Things (IoT) systems. In this work, we investigate the real-time wireless control over LAWNs, where an aerial drone is employed to serve multiple mobile automated guided vehicles (AGVs) via finite blocklength (FBL) transmission. Toward this end, we adopt the model predictive control (MPC) to ensure accurate trajectory tracking, while we analyze the communication reliability using the outage probability. Subsequently, we formulate an optimization problem to jointly determine control policy, transmit power allocation, and drone trajectory by accounting for the maximum travel distance and control input constraints. To address the resultant non-convex optimization problem, we first derive the closed-form expression of the outage probability under FBL transmission. Based on this, we reformulate the original problem as a quadratic programming (QP) problem, followed by developing an alternating optimization (AO) framework. Specifically, we employ the projected gradient descent (PGD) method and the successive convex approximation (SCA) technique to achieve computationally efficient sub-optimal solutions. Furthermore, we thoroughly analyze the convergence and computational complexity of the proposed algorithm. Extensive simulations and AirSim-based experiments are conducted to validate the superiority of our proposed approach compared to the baseline schemes in terms of control performance.

Recently, Named Data Networking (NDN) has garnered widespread attention in academia as an innovative network architecture, offering solutions to challenges such as the vulnerability of end-to-end connections in IP-based networks. In NDN, nodes utilize a “pull-push” architecture, exchangingInterestandDatapackets for communication. This architecture is particularly well-suited for highly dynamic, topology-varying unmanned aerial vehicle (UAV) swarm networks, known as UAV Named Data Networking (UNDN). However, in UNDN, due to constraints such as the lightweight design and limited energy of UAVs, the UAVs may exhibit selfish behaviors, opting not to share data in order to conserve their own energy consumption. This behavior results in degraded network performance, as the lack of cooperation among UAVs can hinder efficient data sharing and communication. Therefore, an effective incentive mechanism needs to be proposed. In this paper, we formulate the content-sharing process in UNDN as a double auction market for data exchange. To tackle the problem of asymmetric information between content consumers and producers, we propose an Iterative Double Auction algorithm (IDAA). This algorithm introduces a virtual central broker to guide both parties in conducting honest auctions. Furthermore, we develop a diffusion model-based reinforcement learning algorithm (DiffRL-DA) to derive optimal auction policies, with the goal of better capturing market behaviors and overcoming the limitations of the IDAA. Finally, simulation results verify the efficacy of our proposed mechanisms.

Despite the widespread deployment of terrestrial networks, providing reliable communication services to remote areas and maintaining connectivity during emergencies remains challenging. Low Earth orbit (LEO) satellite constellations offer promising solutions with their global coverage capabilities and reduced latency, yet struggle with intermittent coverage and limited communication windows due to orbital dynamics. This paper introduces an age of information (AoI)-aware space-air-ground integrated network (SAGIN) architecture that leverages a high-altitude platform (HAP) as intelligent relay between the LEO satellites and ground terminals. Our three-layer design employs hybrid free-space optical (FSO) links for high-capacity satellite-to-HAP communication and reliable radio frequency (RF) links for HAP-to-ground transmission, and thus addressing the temporal discontinuity in LEO satellite coverage while serving diverse user priorities. Specifically, we formulate a joint optimization problem to simultaneously minimize the AoI and satellite handover frequency through optimal transmit power distribution and satellite selection decisions. This highly dynamic, non-convex problem with time-coupled constraints presents significant computational challenges for traditional approaches. To address these difficulties, we propose a novel diffusion model (DM)-enhanced dueling double deep Q-network withaction decomposition andstate transformer encoder (DD3QN-AS) algorithm that incorporates transformer-based temporal feature extraction and employs a DM-based latent prompt generative module to refine state-action representations through conditional denoising. Simulation results highlight the superior performance of the proposed approach compared with policy-based methods and some other deep reinforcement learning (DRL) benchmarks. Moreover, performance analysis under various system settings verifies the robustness of the proposed approach.

The rapid development of the low-altitude economy (LAE) has significantly increased the utilization of autonomous aerial vehicles (AAVs) in various applications, necessitating efficient and secure communication methods among AAV swarms. In this work, we aim to introduce distributed collaborative beamforming (DCB) into AAV swarms and handle the eavesdropper collusion by controlling the corresponding signal distributions. Specifically, we consider a two-way DCB-enabled aerial communication between two AAV swarms and construct these swarms as two AAV virtual antenna arrays. Then, we minimize the two-way known secrecy capacity and maximum sidelobe level to avoid information leakage from the known and unknown eavesdroppers, respectively. Simultaneously, we also minimize the energy consumption of AAVs when constructing virtual antenna arrays. Due to the conflicting relationships between secure performance and energy efficiency, we consider these objectives by formulating a multi-objective optimization problem, which is NP-hard and with a large number of decision variables. Accordingly, we design a novel generative swarm intelligence (GenSI) framework to solve the problem with less overhead, which contains a conditional variational autoencoder (CVAE)-based generative method and a proposed powerful swarm intelligence algorithm. In this framework, CVAE can collect expert solutions obtained by the swarm intelligence algorithm in other environment states to explore characteristics and patterns, thereby directly generating high-quality initial solutions in new environment factors for the swarm intelligence algorithm to search solution space efficiently. Simulation results show that the proposed swarm intelligence algorithm outperforms other state-of-the-art baseline algorithms, and the GenSI can achieve similar optimization results by using far fewer iterations than the ordinary swarm intelligence algorithm. Experimental tests demonstrate that introducing the CVAE mechanism achieves a 58.7% reduction in execution time, which enables the deployment of GenSI even on AAV platforms with limited computing power.

The rising data demands of generative AI models, such as large language models (LLMs), underscore the value of utilizing edge device data in mobile computing, where federated learning (FL) provides a privacy-preserving approach via decentralized model training. To address data heterogeneity across edge devices, federated multi-view learning (FedMVL) has been proposed to improve global model performance by capturing consistency and complementarity among diverse data views. However, existing methods often assume ideal conditions and neglect data uncertainty in mobile edge devices environments. To overcome these challenges, we propose Federated Reliable Multi-view Classification (FedRMVL), a vertical FedMVL framework incorporates Subjective Logic for lightweight uncertainty quantification at local edge devices and applies the Dempster-Shafer combination rule for adaptive and reliable multi-view opinion fusion at the server. Additionally, a partial parameter-sharing strategy is introduced to address feature dimension heterogeneity during federated optimization. The effectiveness and robustness of FedRMVL are validated through theoretical analysis and extensive experiments on real-world datasets.

Collaborative perception can significantly enhance the perceptual capabilities of autonomous vehicles by sharing sensing information through vehicular communications. However, large-scale sharing of sensing information often results in unsustainable network loads, making it challenging to maximize perception performance with limited communication resources in complex environments. To address this challenge, we propose FullPerception, an innovative cooperative perception framework that jointly orchestrates sensing information sharing and communication resource allocation at the network level. FullPerception advocates for the sharing of semantic information (neural network features) within critical areas, i.e., blind spots. With limited communication resources, FullPerception strategically eliminates these blind spots to maximize the accumulated perception performance. We formulate this strategy as a weighted optimization problem and prove its NP-hardness. We propose a simple yet effective algorithm, Proactive Conflict-free Scheduling (PCS), which guarantees a good performance ratio by considering broader contexts. PCS is meticulously combined with recursive structure, accounting for both the overall and future contexts to determine link scheduling and resource allocation. We demonstrate that FullPerception improves perception accuracy by 20% relative to single-vehicle systems and by 10% compared to existing scheduling methods through large-scale comprehensive joint simulation experiments.

Large language models are increasingly deployed across mobile and edge environments, where privacy-sensitive and heterogeneous user data raise critical concerns of copyright infringement, data leakage, and regulatory non-compliance. Ma chine unlearning has thus emerged as an essential capability to remove the influence of specific data without full retraining. However, two key challenges remain open: 1) how to quantify unlearning to enable data valuation without retraining, especially since the massive scale of pretraining makes it infeasible to evaluate the contribution of individual data samples in advance, and 2) how to verify the correctness without retraining to ensure that third-party auditors can efficiently confirm the complete removal of targeted data influence. To address the aforementioned challenges, in this paper, we design a dual-stage machine unlearning framework to quantify the contribution of forgotten data and certify data removal without full retraining, serving as an auditing layer for first-order unlearning methods. Specifically, we design a run-time Shapley value-based unlearned data evaluation mechanism that utilizes a first-order approximation strategy to estimate the marginal contribution of forgotten samples. Moreover, we propose a proof of unlearning mechanism that generates compact, auditable artifacts of the unlearning process to efficiently verify that the targeted data influence has been completely removed. Compared with five state-of-the-art unlearning baselines, our approach achieves effectiveness in data valuation, stronger guarantees of removal correctness, and lower computational overhead.

With the rapid development of vehicle-to-everything (V2X) technology, service migration has become an important approach to provide low-latency computing services and ensure service continuity for high-speed moving vehicles in vehicular edge computing (VEC), which enables VEC to efficiently support advanced transportation services. However, optimizing service satisfaction for service migration in multi-vehicle heterogeneous VEC networks is challenging, since the complex, multifactorial, and nonlinear dependencies between service satisfaction and quality of service (QoS) metrics is intractable, and the rapidly changing computational loads in edge server results in inefficient utilization of edge resources. In this paper, we propose a service Satisfaction-based Adaptive service Migration and resource Allocation joint Optimization scheme (SAMAO) to improve service migration efficiency and edge resource utilization in VEC. Firstly, we develop an adaptive computation resource allocation algorithm that can adjust resource allocation strategy according to load status of edge servers to improve vehicle service satisfaction. Then, to minimize energy consumption and ensure service satisfaction for vehicles, we propose a utility maximization algorithm to formulate migration decisions based on pre-allocated computation resources on servers. Finally, numerous simulations based on Shanghai Telecom real-world dataset show that SAMAO can achieve significant advantages in terms of average service satisfaction and computation cost.

Generative AI (GenAI) has emerged as a transformative technology, enabling customized and personalized AI-generated content (AIGC) services. In this paper, we address challenges of edge-enabled AIGC service provisioning, which remain underexplored in the literature. These services require executing GenAI models with billions of parameters, posing significant obstacles to resource-limited wireless edge. We subsequently introduce the formulation of joint model caching and resource allocation for AIGC services to balance a trade-off between AIGC quality and latency metrics. We obtain mathematical relationships of these metrics with the computational resources required by GenAI models via experimentation. Afterward, we decompose the formulation into a model caching subproblem on a long-timescale and a resource allocation subproblem on a short-timescale. Since the variables to be solved are discrete and continuous, respectively, we leverage a double deep Q-network (DDQN) algorithm to solve the former subproblem and propose a diffusion-based deep deterministic policy gradient (D3PG) algorithm to solve the latter. The proposed D3PG algorithm makes an innovative use of diffusion models as the actor network to determine optimal resource allocation decisions. Consequently, we integrate these two learning methods within the overarching two-timescale deep reinforcement learning (T2DRL) algorithm, the performance of which is studied through comparative numerical simulations.

Due to the massive computational demands of large generative models, AI-Generated Content (AIGC) can organize collaborative Mobile AIGC Service Providers (MASPs) at network edges to provide ubiquitous and customized content generation for resource-constrained users. However, such a paradigm faces two significant challenges: i) raw prompts (i.e., the task description from users) often lead to poor generation quality due to users' lack of experience with specific AIGC models, and ii) static service provisioning fails to efficiently utilize computational and communication resources given the heterogeneity of AIGC tasks. To address these challenges, we propose an intelligent mobile AIGC service scheme. Firstly, we develop an interactive prompt engineering mechanism that leverages a Large Language Model (LLM) to generate customized prompt corpora and employs Inverse Reinforcement Learning (IRL) for policy imitation through small-scale expert demonstrations. Secondly, we formulate a dynamic mobile AIGC service provisioning problem that jointly optimizes the number of inference trials and transmission power allocation. Then, we propose the Diffusion Enhanced Deep Deterministic Policy Gradient (D3PG) algorithm to solve the problem. By incorporating the diffusion process into Deep Reinforcement Learning (DRL) architecture, the environment exploration capability can be improved, thus adapting to varying mobile AIGC scenarios. Extensive experimental results demonstrate that our prompt engineering approach improves single-round generation success probability by 6.3×, while D3PG increases the user service experience by 50.3% compared to baseline DRL approaches.

The vehicular metaverse is a novel physical-virtual fusion realm that aims to disrupt the current transportation paradigm. Within this landscape, the coexistence of moving vehicles and their digital counterparts inevitably brings new privacy concerns. Pseudonym exchange, where vehicles exchange temporary identifiers with neighbors to enhance anonymity, offers an affordable solution to protect the location privacy of vehicles. However, existing pseudonym exchange schemes primarily focus on physical vehicles, limiting their effectiveness across physical and virtual spaces in the vehicular metaverse. Furthermore, studies have shown that many vehicles care little about their location privacy, so incentivizing more vehicles to participate in pseudonym exchanges remains a challenge. Motivated by these issues, we propose a physical-virtual dual pseudonym exchange scheme, incorporating an Attribute-Matched Double Dutch Auction (AMDDA) incentive mechanism to facilitate pseudonym exchange transactions. We use a trajectory prediction model to evaluate vehicle attributes, ensuring pseudonym exchange between vehicles with high trajectory similarity to enhance location privacy preservation. Furthermore, we devise a Generative Diffusion Model (GDM)-based approach to derive the optimal pricing strategy in the AMDDA market. Extensive experiments on real-world datasets demonstrate that the proposed scheme significantly improves both the efficiency and degree of location privacy protection.

Edge Intelligence (EI) combines edge computing and artificial intelligence to deliver low-latency and resource-efficient services. Integrated Sensing and Communication (ISAC) further empowers EI by enhancing edge perception and accelerating intelligent model training. However, integrating ISAC into EI complicates the coordination of dynamically varying sensing, communication, and computation resources, especially under device mobility and unpredictable network conditions, leading to degraded service performance. To address these coordination challenges and sustain high-quality service under mobility and dynamics, we aim to design an adaptive service provision framework that tightly couples real-time perception with intelligent decision-making at the edge. Specifically, we propose an adaptive service provision architecture for ISAC-assisted EI, where Digital Twins (DTs) hosted on edge servers represent edge devices and their contexts to enable accurate perception and intelligent decision-making, thereby enhancing the efficiency of ISAC-enabled services. By dynamically migrating DTs across edge servers based on device mobility and resource availability, the system supports continuous decision-making and seamless service delivery. We further integrate convex optimization for efficient multi-resource coordination and a Time-Varying Contextual Bandit (TVCB) algorithm to enable adaptive, context-aware DT migration in dynamic environments. Extensive simulations demonstrate that our approach significantly improves service quality, reliability, and adaptability in ISAC-assisted EI systems, reducing migration oscillations and overhead while achieving lower latency and higher utility compared with representative baselines.

With the widespread adoption of location-based services (LBS), user-generated trajectory data shows strong spatiotemporal correlation, rendering it highly vulnerable to inference attacks that expose sensitive information. In particular, once semantic locations like “hospital” and “bank” are identified, the risk of trajectory leakage increases substantially. To address this issue, this paper formulates a personalized spatiotemporal trajectory privacy protection framework, which is designed to protect locations with varying semantic sensitivities on the trajectory from the attacker with spatiotemporal correlation information. We model the trajectory privacy protection problem as a Markov Decision Process (MDP) and introduce the reinforcement learning (RL) technique to adjust the privacy parameters dynamically. Specifically, we leverage the twin delayed deep deterministic policy gradient (TD3) algorithm to enhance the stability and accuracy of policy evaluation, enabling efficient learning of optimal policies in continuous action spaces. Furthermore, a safe exploration strategy is incorporated to continuously evaluate and avoid high-risk state-action pairs, thereby enhancing privacy protection. Simulation results demonstrate that the proposed mechanism significantly improves privacy protection while effectively reducing Quality of Service (QoS) loss, exhibiting better convergence and overall system utility.

Multi-access Edge Computing (MEC) enables users to handle resource-intensive and latency-sensitive tasks. However, the offloading behaviors, which are closely correlated with wireless channel conditions, can inadvertently reveal users' location information to untrustworthy MEC servers. Existing location privacy-aware task offloading (LPTO) mechanisms have not fully considered and comprehensively analyzed personalized location privacy protection requirements. To address this gap, this paper proposes a differential privacy (DP)-based personalized LPTO mechanism for MEC environments that jointly optimizes the perturbation region, privacy budget, and offloading rate while maximizing the offloading utility. We quantify personalized privacy requirements by incorporating task sensitivity, user privacy preference, and task priority. Then, we propose a two-timescale (2Ts) optimization framework to solve the complex personalized location privacy-aware task offloading optimization problem. Specifically, we optimize the perturbation region on a long timescale to align with long-term privacy requirements. In contrast, the offloading ratio and privacy budget are dynamically optimized on a short timescale based on instantaneous channel states and offloading workloads. Furthermore, we model the privacy-aware offloading problem as a Markov decision process (MDP) and develop a dual-agent deep reinforcement learning (DRL)-based personalized LPTO mechanism (DDPLM) to optimize strategies under dynamic MEC systems. Simulation results validate that the proposed DDPLM achieves personalized location privacy protection while reducing computational costs.

Collaborative mobile edge computing (MEC) has emerged as a promising paradigm to enable low-capability edge nodes to cooperatively execute computation-intensive tasks. However, straggling edge nodes (stragglers) significantly degrade the performance of MEC systems by prolonging computation latency. While coded distributed computing (CDC) as an effective technique is widely adopted to mitigate straggler effects, existing CDC schemes exhibit two critical limitations: (i) They cannot successfully decode the final result unless the number of received results reaches a fixed recovery threshold, which seriously restricts their flexibility; (ii) They suffer from inherent poles in their encoding/decoding functions, leading to decoding inaccuracies and numerical instability in the computational results. To address these limitations, this paper proposes an approximated CDC scheme based on barycentric rational interpolation. The proposed CDC scheme offers several outstanding advantages. Firstly, it can decode the final result leveraging any returned results from workers. Secondly, it supports computations over both finite and real fields while ensuring numerical stability. Thirdly, its encoding/decoding functions are free of poles, which not only enhances approximation accuracy but also achieves flexible accuracy tuning. Fourthly, it integrates a novel BRI-based gradient coding algorithm accelerating the training process while providing robustness against stragglers. Finally, experimental results reveal that the proposed scheme is superior to existing CDC schemes in both waiting time and approximate accuracy.

Vehicular fog computing (VFC) has emerged as a promising paradigm, which leverages the idle computational resources of nearby fog vehicles (FVs) to complement the computing capabilities of conventional vehicular edge computing. However, utilizing VFC to meet the delay-sensitive and computation-intensive requirements of the FVs poses several challenges. First, the limited resources of road side units (RSUs) struggle to accommodate the growing and diverse demands of vehicles. This limitation is further exacerbated by the information asymmetry between the controller and FVs due to the reluctance of FVs to disclose private information and to share resources voluntarily. This information asymmetry hinders the efficient resource allocation and coordination. Second, the heterogeneity in task requirements and the varying capabilities of RSUs and FVs complicate efficient task offloading, thereby resulting in inefficient resource utilization and potential performance degradation. To address these challenges, we first present a hierarchical VFC architecture that incorporates the computing capabilities of both RSUs and FVs. Then, we formulate a delay minimization optimization problem (DMOP), which is an NP-hard mixed integer nonlinear programming (MINLP) problem. To solve the DMOP, we propose a joint computing resource allocation and task offloading approach (JCRATOA), which comprises the components of computing resource allocation and task offloading. Specifically, we propose a convex optimization-based method for RSU resource allocation and a contract theory-based incentive mechanism for FV resource allocation. Moreover, we present a two-sided matching method for task offloading by employing the matching game. Additionally, we theoretically prove the polynomial complexity of JCRATOA. Simulation results demonstrate that the proposed JCRATOA outperforms the benchmark approaches, achieving at least 7.6%, 6.6%, 6.25%, and 11.9% improvements in terms of the task completion delay, task completion ratio, system throughput, and resource utilization fairness, respectively, while satisfying the energy constraints of task vehicles (TVs), RSUs, and FVs.

Semantic communications (SemCom) provide efficient transmission for mobile edge computing (MEC) services by extracting critical semantics from raw information. Although widely adopted in various scenarios, existing single-modal SemCom systems struggle to efficiently support edge multimodal data transmission. Additionally, mobile end users have varying communication requirements across different modalities. However, existing work lacks the ability to generate personalized communication policies tailored to diverse intents (Typically, communication policies include bandwidth allocation and modulation and coding schemes, etc.). In this paper, we propose an edge Cognitive SemCom Agent (CSCA) to facilitate edge multimodal SemCom. Specifically, CSCA leverages an edge Large AI Model (LAM) to realize modality alignment and natural language intent understanding. Moreover, we develop a communication planning module to realize the planning capability, which generates personalized wireless communication policies based on LAM’s environment and intent cognition. Particularly, to assess the efficiency of communication policies in multimodal SemCom and capture intent competition, we present a novel indicator named cognitive SemCom quality indicator (CSCQI). Then, we use the denoising diffusion probabilistic model to optimize the generation policy. Extensive experimental results demonstrate that CSCA achieves an average improvement in intent satisfaction rate and semantic accuracy by 42.19% and 29.75% respectively, while reducing communication delay by 33.40% .

The growing demand for intelligent mobile applications has made the deployment and operation of Deep Neural Networks (DNNs) on mobile Edge Devices (EDs) increasingly essential. However, the highly dynamic nature of edge environments and the limited computational resources of EDs result in significant energy consumption and compromised inference quality. To address these issues, we propose the Demand-Aware Evolutionary Reinforcement Learning (DA-ERL) framework, a novel approach for optimizing Partitioned Collaborative Inference (PCI) across multiple EDs and Mobile Edge Computing (MEC) servers. At the core of DA-ERL is a Demand-Aware Spatio-Temporal Graph Convolutional Network (DA-STGCN). This new architecture creates a predictive state representation by uniquely integrating two channels: a Spatial Graph Channel using Graph Convolutional Networks to model the network topology, and a Temporal Prediction Channel using Temporal Convolutional Networks to capture the evolution of system dynamics. Moreover, we design and formulate a task dynamic demand index to model the dynamic task characteristics, which guides the agent's learning policy. Furthermore, we train DA-ERL within a Cross-Entropy Method (CEM) based evolutionary framework that leverages elite-guided exploration to enhance sample efficiency in complex search spaces. Extensive simulations demonstrate that the proposed DA-ERL framework significantly outperforms conventional methods, achieving a 23.4% reduction in system cost while maintaining a near-perfect task completion rate in high-density scenarios.

The integration of emerging uncrewed aerial vehicle (UAV) with artificial intelligence (AI) and ground-embedded robots (GERs) has transformed emergency rescue operations in unknown environments. However, the high computational demands of such missions often exceed the capacity of a single UAV, making it difficult for the system to continuously and stably provide high-level services. To address these challenges, this paper proposes a novel cooperation framework involving UAVs, GERs, and airships. This framework enables resource pooling through UAV-to-GER (U2G) and UAV-to-airship (U2A) communications, providing computing services for UAV offloaded tasks. Specifically, we formulate the multi-objective optimization problem of task assignment and exploration optimization in UAVs as a dynamic long-term optimization problem. Our objective is to minimize task completion time and energy consumption while ensuring system stability over time. To achieve this, we first employ the Lyapunov optimization method to transform the original problem, with stability constraints, into a per-slot deterministic problem. We then propose an algorithm named HG-MADDPG, which combines the Hungarian algorithm with a generative diffusion model (GDM)-based multi-agent deep deterministic policy gradient (MADDPG) approach, to jointly optimize exploration and task assignment decisions. In HG-MADDPG, we first introduce the Hungarian algorithm as a method for exploration area selection, enhancing UAV efficiency in interacting with the environment. We then innovatively integrate the GDM and multi-agent deep deterministic policy gradient (MADDPG) to optimize task assignment decisions, such as task offloading and resource allocation. Simulation results demonstrate the effectiveness of the proposed approach, with significant improvements in task offloading efficiency, latency reduction, and system stability compared to baseline methods.

Through conducting equivalent model training within the paradigm of edge intelligence, the Digital Twin Edge Networks (DITEN) have been widely employed in the Industrial Internet-of-Things (IIoT) to facilitate the cost-effective execution without the operational disruption. However, due to the insufficient consideration of heterogeneity in computing and communication capabilities of distinct industrial terminals in the Digital Twin (DT) model training, the existing approaches of DT construction/update have unbalanced model training cost and loss in the whole life cycle of DT model, hindering the abilities of quick responding to complex and dynamic productions and ensuring the data consistency of virtual-real space. To address this issue, we define a global loss minimization problem with constraint, and propose an original approach of semi-asynchronous federated learning, named EDT-SaFL, as a promising solution. Considering the collaborative utilization of heterogeneous resources, and the contribution of local data quantity and quality to the global model update, the EDT-SaFL consists of three important operations,Terminal Selection for Model Training,Self-Adaptation of Local Training Iterations, andSemi-asynchronous Global Aggregation. With the analysis of convergence, complexity and communication overhead, the experiments have evidently demonstrated the superiority of EDT-SaFL on the datasets of CIFAR-10 and Industrial-Equipment.

Edge intelligence deploys artificial intelligence models on edge nodes proximal to data sources, and delivers real-time inference support for resource-constrained devices. To realize this vision, inference offloading differs from conventional computation offloading by tailoring offloading strategies to the intrinsic characteristics of AI inference tasks. In this field, existing researchs generally lack fine-grained model partitioning capabilities and long-term resource adaptability, failing to optimize resource utilization and sustain stable performance in mobile environments. To address these issues, we propose an adaptive inference acceleration framework that dynamically partitions inference models into hierarchical subtasks and offloads these subtasks to heterogeneous edge servers. We formulate a joint optimization problem for task partitioning, offloading and resource allocation, which takes queue stability as the constraint and aims to minimize the long-term average task completion time. To realize the optimal trade-off between latency and stability without future state prediction, we adopt Lyapunov optimization to decompose the long-term stochastic optimization into slot-by-slot solvable deterministic subproblems. For these slot-by-slot subproblems, we design a Q-network Mixing (QMIX)-based multi-agent reinforcement learning method to enable collaborative strategy selection across edge servers. Experimental simulations show that, compared with baseline algorithms including the greedy, genetic and MAD2RL methods, our proposed framework achieves a substantial reduction in task completion time while preserving inference accuracy and queue stability.

The integration of satellite and autonomous aerial vehicle (AAV) communications has become essential for the scenarios requiring both wide coverage and rapid deployment, particularly in remote or disaster-stricken areas where the terrestrial infrastructure is unavailable. Furthermore, emerging applications increasingly demand simultaneous mobile edge computing (MEC) and data collection (DC) capabilities within the same aerial network. However, jointly optimizing these operations in heterogeneous satellite-AAV systems presents significant challenges due to limited on-board resources and competing demands under dynamic channel conditions. In this work, we investigate a satellite-AAV-enabled joint MEC-DC system where these platforms collaborate to serve ground devices (GDs). Specifically, we formulate a joint optimization problem to minimize the average MEC end-to-end delay and AAV energy consumption while maximizing the collected data. Since the formulated optimization problem is a non-convex mixed-integer nonlinear programming (MINLP) problem, we propose a Q-weighted variational policy optimization-based joint AAV movement control, GD association, offloading decision, and bandwidth allocation (QAGOB) approach. Specifically, we reformulate the optimization problem as an action space-transformed Markov decision process to adapt the variable action dimensions and hybrid action space. Subsequently, QAGOB leverages the multi-modal generation capacities of diffusion models to optimize policies and can achieve better sample efficiency while controlling the diffusion costs during training. Simulation results show that QAGOB outperforms five other benchmarks, including traditional DRL and diffusion-based DRL algorithms. Furthermore, the MEC-DC joint optimization achieves significant advantages when compared to the separate optimization of MEC and DC.

Edge intelligence enhances the computational capabilities of resource-limited devices by offloading inference tasks to edge servers. Traditional methods either execute the entire model on the device, resulting in slow inference, or fully offload it to the server, incurring communication delays and privacy risks due to raw data transmission. Model partitioning addresses these challenges by splitting the model for execution on both the device and edge server, transmitting only intermediate inference results. However, current model partitioning methods lack consideration of device mobility, resulting in reduced inference efficiency and task interruptions. To address these limitations, we introduce MobiSplit, a novel mobility-aware framework that dynamically partitions inference models between resource-constrained devices and edge servers. MobiSplit adapts to real-time device mobility, fluctuating network conditions, and computational constraints to minimize inference latency and energy consumption while ensuring robust task execution. Additionally, we propose a distributed auction-based algorithm that empowers edge devices to autonomously determine optimal partitioning and offloading strategies in a scalable and adaptive manner. Extensive simulations demonstrate that MobiSplit enhances inference efficiency, achieving a 60% latency reduction and a 20% energy consumption decrease compared to the best-performing baseline across diverse edge scenarios.

As terrestrial resources become increasingly saturated, the developing attention is gradually shifting from the ground to the low-altitude airspace, which supports many emerging applications such as urban air taxis and aerial inspection. For these applications, low-altitude wireless networks (LAWNs) are the foundation, with integrated sensing, communications, and computing (ISCC) being one of the core parts. However, the openness of low-altitude airspace poses a serious threat to communications, degrading ISCC performance and ultimately compromising the reliability of applications supported by LAWNs. To address these challenges, this paper studies joint performance optimization of ISCC while considering security of the communications. Specifically, we derive beampattern error, secrecy rate, and age of information (AoI) as performance metrics for sensing, secure communication, and computing. Building on these metrics, we formulate a multi-objective optimization problem, which aims to balance sensing and computing performance while enhancing the secrecy rate of communications. We then propose a deep Q-network (DQN)-based multi-objective evolutionary algorithm, which adaptively selects evolutionary operators according to the evolving optimization objectives, thereby leading to more effective solutions. Extensive simulations show that the proposed method brings an average performance gain of about 14% compared to existing methods, thereby ensuring ISCC performance for applications supported by LAWNs.

To enable training of large artificial intelligence (AI) models at the network edge, split federated learning (SFL) has emerged as a promising approach by distributing computation between edge devices and a server. However, while unstable network environments pose significant challenges to SFL, prior schemes often overlook such an effect by assuming perfect client participation, rendering them impractical for real-world scenarios. In this work, we develop an optimization framework for SFL with unstable client participation. We theoretically derive the first convergence upper bound for SFL with unstable client participation by considering activation uploading failures, gradient downloading failures, and model aggregation failures. Based on the theoretical results, we formulate a joint optimization problem for client sampling and model splitting to minimize the upper bound. We then develop an efficient solution approach to solve the problem optimally. Extensive simulations on EMNIST and CIFAR-10 demonstrate the superiority of our proposed framework compared to existing benchmarks.

Low-Altitude Economy Networks (LAENets) are emerging as a promising paradigm to support various low-altitude services through integrated air-ground infrastructure. To satisfy low-latency and high-computation demands, the integration of Unmanned Aerial Vehicles (UAVs) with Mobile Edge Computing (MEC) systems plays a vital role, which offloads computing tasks from terminal devices to nearby UAVs, enabling flexible and resilient service provisions for ground users. To promote the development of LAENets, it is significant to achieve low-carbon multi-UAV-assisted MEC networks. However, several challenges hinder this implementation, including the complexity of multi-dimensional UAV modeling and the difficulty of multi-objective coupled optimization. To this end, this paper proposes a novel Retrieval Augmented Generation (RAG)-based Large Language Model (LLM) agent framework for model formulation. Specifically, we develop HybridRAG by combining KeywordRAG, VectorRAG, and GraphRAG, empowering LLM agents to efficiently retrieve structural information from expert databases and generate more accurate optimization problems compared with traditional RAG-based LLM agents. After customizing carbon emission optimization problems for multi-UAV-assisted MEC networks, we propose a Double Regularization Diffusion-enhanced Soft Actor-Critic (R2DSAC) algorithm to solve the formulated multi-objective optimization problem. The R2DSAC algorithm incorporates diffusion entropy regularization and action entropy regularization to improve the performance of the diffusion policy. Furthermore, we dynamically mask unimportant neurons in the actor network to reduce the carbon emissions associated with model training. Simulation results demonstrate the reliability of the proposed HybridRAG-based LLM agent framework, which achieves a$6.6\%$improvement in F1 scores over traditional RAG, and validate the effectiveness of the R2DSAC algorithm, which outperforms the SAC algorithm by up to$64.17\%$.

With rapid advancements in large language models (LLMs), AI-generated content (AIGC) has emerged as a key driver of technological innovation and economic transformation. Personalizing AIGC services to meet individual user demands is essential but challenging for AIGC service providers (ASPs) due to the subjective and complex demands of mobile users (MUs), as well as the computational and communication resource constraints faced by ASPs. To tackle these challenges, we first develop a novel multi-dimensional quality-of-experience (QoE) metric. This metric comprehensively evaluates AIGC services by integrating accuracy, token count, and timeliness. We focus on a mobile edge computing (MEC)-enabled AIGC network, consisting of multiple ASPs deploying differentiated AIGC models on edge servers and multiple MUs with heterogeneous QoE requirements requesting AIGC services from ASPs. To incentivize ASPs to provide personalized AIGC services under MEC resource constraints, we propose a QoE-driven incentive mechanism. We formulate the problem as an equilibrium problem with equilibrium constraints (EPEC), where MUs as leaders determine rewards, while ASPs as followers optimize resource allocation. To solve this, we develop a dual-perturbation reward optimization algorithm, reducing the implementation complexity of adaptive pricing. Experimental results demonstrate that our proposed mechanism achieves a reduction of approximately$64.9\%$in average computational and communication overhead, while the average service cost for MUs and the resource consumption of ASPs decrease by$66.5\%$and$76.8\%$, respectively, compared to state-of-the-art benchmarks.

Semantic communication has emerged as a promising paradigm in next-generation communication systems, leveraging advanced artificial intelligence (AI) models to extract and transmit semantic representations for efficient information exchange. However, the reliability of received information is often compromised by unpredictable semantic noise, such as corruptions or distortions in the transmitted representations. Traditional methods typically rely on adversarial training with artificially injected noise to improve robustness. Yet, these approaches suffer from limited adaptability to varying noise conditions and incur considerable computational overhead during training. To address these challenges, this paper introduces Semantic communication with High-and-Low Frequency Decomposition (Se-HiLo), a novel noise-resilient scheme designed for image transmission. Se-HiLo integrates a Finite Scalar Quantization (FSQ) module that enhances robustness by constraining encoded representations within predefined discrete spaces, thereby eliminating the need for adversarial training. While FSQ strengthens resistance to noise, it inherently limits representational expressiveness. To mitigate this trade-off, Se-HiLo further incorporates a transformer-based high-and-low frequency decomposition module that separates image representations into distinct frequency components and encodes them into independent FSQ spaces, thus preserving semantic diversity and expressiveness. Extensive experiments validate that Se-HiLo significantly improves noise robustness and maintains accurate semantic communication across a wide range of noise environments.

Autonomous aerial vehicle (AAV) target tracking technology is an essential component for enabling diverse low-altitude activities. Due to the constraints on energy and computing resources of AAVs, current approaches face challenges in balancing prolonged flight duration with precise tracking while avoiding high computational complexity. Therefore, this paper proposes an energy-aware formation control algorithm for multiple AAVs to cooperatively track a target while retaining a desired formation pattern. Firstly, to achieve a balanced outcome in terms of tracking performance and control effort, an actor-critic based learning predictive rule is explored to develop a near-optimal control protocol that stabilizes error dynamics and minimizes value functions for discrete-time AAV systems. By decomposing the infinite-horizon target tracking problem into a sequence of finite-horizon sub-problems, the reinforcement learning (RL)-based predictive control algorithm can achieve fast convergence in approximating the solution of Hamilton-Jacobi-Bellman (HJB) equation. Furthermore, by employing a delicately designed asynchronous policy iteration mechanism with adjustable learning intervals in RL, the cumbersome learning process can be effectively mitigated, thereby attaining both high learning efficiency and a reduced computational burden simultaneously. The involved errors are proven to be convergent and simulation results validate the optimality of our method.

Emerging technologies in sixth generation (6G) of wireless communications, such as terahertz communication and ultra-massive multiple-input multiple-output, present promising prospects. Despite the high data rate potential of millimeter wave communications, millimeter wave (mmWave) communications in urban low altitude economy (LAE) environments are constrained by challenges such as signal attenuation and multipath interference. Specially, in urban environments, mmWave communication experiences significant attenuation due to buildings, owing to its short wavelength, which necessitates developing innovative approaches to improve the robustness of such communications in LAE networking. In this paper, we explore the use of an unmanned aerial vehicle (UAV)-carried intelligent reflecting surface (IRS) to support low altitude mmWave communication. Specifically, we consider a typical urban low altitude communication scenario where a UAV-carried IRS establishes a line-of-sight (LoS) channel between the mobile users and a source user (SU) despite the presence of obstacles. Subsequently, we formulate an optimization problem aimed at maximizing the transmission rates and minimizing the energy consumption of the UAV by jointly optimizing phase shifts of the IRS and UAV trajectory. Given the non-convex nature of the problem and its high dynamics, we propose a deep reinforcement learning-based approach incorporating neural episodic control, long short-term memory, and an IRS phase shift control method to enhance the stability and accelerate the convergence. Simulation results show that the proposed algorithm effectively resolves the problem and surpasses other benchmark algorithms in various performances.

It is significant to employ multiple autonomous underwater vehicles (AUVs) to execute the underwater target tracking task collaboratively. However, it's pretty challenging to meet various prerequisites utilizing traditional control methods. Therefore, we propose an effective two-stage learning from demonstrations training framework, FISHER, to highlight the adaptability of reinforcement learning (RL) methods in the multi-AUV underwater target tracking task, while addressing its limitations such as extensive requirements for environmental interactions and the challenges in designing reward functions. The first stage utilizes imitation learning (IL) to realize policy improvement and generate offline datasets. To be specific, we introduce multi-agent discriminator-actor-critic based on improvements of the generative adversarial IL algorithm and multi-agent IL optimization objective derived from the Nash equilibrium condition. Then in the second stage, we develop multi-agent independent generalized decision transformer, which analyzes the latent representation to match the future states of high-quality samples rather than reward function, attaining further enhanced policies capable of handling various scenarios. Besides, we propose a simulation to simulation demonstration generation procedure to facilitate the generation of expert demonstrations in underwater environments, which capitalizes on traditional control methods and can easily accomplish the domain transfer to obtain demonstrations. Extensive simulation experiments from multiple scenarios showcase that FISHER possesses strong stability, multi-task performance and capability of generalization.

Mobile cloud computing has become widely adopted for its convenience in data storage and sharing, but it also introduces challenges related to data privacy and security. To address these issues, public key authenticated encryption with keyword search (PAEKS) has emerged as a potential solution that ensures data privacy while resisting internal keyword guessing attacks (IKGAs). Unfortunately, most existing PAEKS schemes have limited adaptability to multi-user scenarios. Specifically, in PAEKS, ciphertext generation requires the participation of users' secret keys, which results in ciphertexts being unique, even when the same keywords are encrypted by different users. Con sequently, the number of trapdoors used to match the ciphertexts grows linearly with the amount of senders. Designing an efficient PAEKS scheme for multiple users remains an open challenge. In this paper, we propose CT-PAEKS, a lattice-based PAEKS scheme with constant trapdoor for data privacy-preserving in mobile cloud computing. CT-PAEKS introduces an additional administrator, enabling the receiver to generate a unified search trapdoor for ciphertexts from multiple senders. Additionally, it allows multiple senders to generate a single ciphertext for the same keyword encryption, thus avoiding ciphertext duplication. Furthermore, CT-PAEKS supports fast search during ciphertext matching, allowing all corresponding ciphertexts to be identified with a single match. We also formalize and prove the security of CT-PAEKS in the random oracle model. Comprehensive perfor mance evaluations indicate that our scheme outperforms prior arts, achieving the 1.7×-2.7× and 2.0×-4.4× reduction in terms of computational and communication overhead, respectively.

In Federated Learning (FL), with parameter aggregated by a central node, the communication overhead is a substantial concern. To circumvent this limitation and alleviate the single point of failure within the FL framework, recent studies have introduced Decentralized Federated Learning (DFL) as a viable alternative. Considering the device heterogeneity, and energy cost associated with parameter aggregation, in this paper, the problem on how to efficiently leverage the limited resources available to enhance the model performance is investigated. Specifically, we formulate a problem that minimizes the loss function of DFL while considering energy and latency constraints. The proposed solution involves optimizing the number of local training rounds across diverse devices with varying resource budgets. To make this problem tractable, we first analyze the convergence of DFL with edge devices with different rounds of local training. The derived convergence bound reveals the impact of the rounds of local training on the model performance. Then, based on the derived bound, the closed-form solutions of rounds of local training in different devices are obtained. Meanwhile, since the solutions require the energy cost of aggregation as low as possible, we modify different graph-based aggregation schemes to solve this energy consumption minimization problem, which can be applied to different communication scenarios. Finally, a DFL framework which jointly considers the optimized rounds of local training and the energy-saving aggregation scheme is proposed. Simulation results show that, the proposed algorithm achieves a better performance than the conventional schemes with fixed rounds of local training, and consumes less energy than other traditional aggregation schemes.

Searchable symmetric encryption (SSE) enables the storage and retrieval of encrypted data on untrusted cloud servers, while dynamic searchable symmetric encryption (DSSE) further supports updating encrypted data. To date, in multi-user environments, most DSSE schemes cannot achieve simultaneous access control for both keyword retrieval and data updates. To address this issue, we propose a new DSSE scheme with efficient and complete(keyword retrieval and update)access control for multi-user environments, named EFCAM. Our work has simultaneously achieved efficient, flexible, and fine-grained access control for keyword retrieval and updating, this is extremely rare in existing research. For update operations, we combine file index encoding and homomorphic encryption (HE) technology, so that EFCAM optimizes the calculation; to achieve flexible access control, we adopt an equality test scheme that can supports three types of update authorization. For retrieval operations, users do not need to share keys. By executing a single query, the users can effectively retrieve all the data that they have permission to access. To enhance system security and operational efficiency, we have extended EFCAM with a dynamic policy update mechanism for flexible and real-time adjustment of access control policies. We formally analyze the security of EFCAM to prove that our scheme has forward security (FS) and backward security (BS). Experimental results show that, EFCAM maintains outstanding efficiency in encrypted data retrieval and update operations within multi-user environments, while also exhibiting strong scalability.

Digital twin (DT) is envisioned not only to perform the high-fidelity virtual representation of its corresponding physical entity (PE), but also to serve as an active agent delivering diverse types of sophisticated services. This paper studies an end-edge-cloud collaborative DT placement and update framework. Specifically, we consider that DTs are dynamically placed across edge servers (ESs) via migration following their paired PEs' potential mobility, while being supported by real-time data fetched from the cloud center and user ends. On top of this, we emphasize a unique feature that DTs should also be continually updated capturing the uncertain evolutions for both personalized service ability improvement and versatile service ability maintenance, where the personalization is improved by utilizing the experiential knowledge from the cloud center and their corresponding PEs, and the versatility is maintained by integrating pre-stored profiles. To maximize the long-term system-wide average weighted quality-of-service (QoS) in handling all types of PEs' service requests under the stringent system cost constraint, we formulate an online problem to jointly optimize DT migrations, service priorities towards various request types, and all related DT updating strategies. To address underlying difficulties, we propose a novel adversarial bandit learning assisted online optimization approach, called ARBOK. We first leverage the Lyapunov decomposition method to transform the long-term problem into multiple instant ones, each of which is further decoupled into two correlated subproblems. For solving one subproblem with a bilinear structure, we develop a McCormick envelopes based algorithm (MO-EL). Besides, we design an extended adversarial combinatorial multi-armed bandit algorithm (AC-BL) to tackle the other subproblem, which constructs a super arm set to resolve the issue of excessively large decision space and employs a robust scheme to handle the inherent uncertainty and non-stationarity in each super arm's loss function. We integrate both algorithms seamlessly into ARBOK and alternately execute them till the convergence. Theoretical analysis and extensive simulations show the effectiveness of the introduced dynamic DT placement and continual update framework, demonstrating that ARBOK can converge to the asymptotic optimum within a polynomial-time complexity while outperforming counterparts.

Sixth Generation (6G)-enabled Internet of Vehicles (IoV) facilitates efficient data synchronization through ultra-fast bandwidth and high-density connectivity, enabling the emergence of Vehicle Twins (VTs). As highly accurate replicas of vehicles, VTs can support intelligent vehicular applications for occupants in 6G-enabled IoV. Thanks to the full coverage capability of 6G, resource-constrained vehicles can offload VTs to edge servers, such as roadside units, unmanned aerial vehicles, and satellites, utilizing their computing and storage resources for VT construction and updates. However, communication between vehicles and edge servers with limited coverage is prone to interruptions due to the dynamic mobility of vehicles. Consequently, VTs must be migrated among edge servers to maintain uninterrupted and high-quality services for users. In this paper, we introduce a VT migration framework in 6G-enabled IoV. Specifically, we first propose a Long Short-Term Memory (LSTM)-based Transformer model to accurately predict long-term workloads of edge servers for migration decision-making. Then, we propose a Dynamic Mask Multi-Agent Proximal Policy Optimization (DM-MAPPO) algorithm to identify optimal migration routes in the highly complex environment of 6G-enabled IoV. Finally, we develop a practical platform to validate the effectiveness of the proposed scheme using real datasets. Simulation results demonstrate that the proposed DM-MAPPO algorithm significantly reduces migration latency by$20.82\%$and packet loss by$75.07\%$compared with traditional deep reinforcement learning algorithms.

The growing adoption of AI-Generated Content (AIGC) has made large-scale processing of multiple Generative AI (GAI) training jobs a key strategy for improving cost-efficiency in computing clusters. However, the distributed nature of GAI models, together with inherent network bottlenecks, imposes significant challenges on system performance. Moreover, differences in training purposes, variations in model sizes, and asynchronous lifecycles create a dynamic environment. As a result, the coexistence of multiple GAI training jobs in a computing cluster exacerbates problems such as resource misallocation, fragmentation, and network contention, leading to low resource utilization and inefficient training performance. These motivate us to explore an efficient resource scheduling approach for completing multiple GAI training jobs. Accordingly, we introduce an intrinsic topology-aware scheduling framework designed to ensure flexible scheduling and efficient distributed training of GAI models. To address the trade-off between the number of concurrent jobs and the communication contention they generate, we formulate a multi-objective optimization problem with two objectives: maximizing the utility of GAI jobs and minimizing communication bandwidth. We then propose the Diffusion Model-based AI-Generated Resources Scheduling (DARS) algorithm, designed to capture dynamic, high-dimensional environments and generate optimal resource scheduling decisions. DARS employs a denoising diffusion process to iteratively refine noisy resource allocations into optimized scheduling decisions. Subsequently, we replace the policy network of Deep Reinforcement Learning (DRL) with DARS to address environmental uncertainty and enhance efficiency. Finally, the simulation results confirm that the proposed algorithm outperforms existing approaches.

This paper introduces a two-stage generative AI (GenAI) framework tailored for temporal spectrum cartography in low-altitude economy networks (LAENets). LAENets, characterized by diverse aerial devices such as UAVs, rely heavily on wireless communication technologies while facing challenges, including spectrum congestion and dynamic environmental interference. Traditional spectrum cartography methods have limitations in handling the temporal and spatial complexities inherent to these networks. Addressing these challenges, the proposed framework first employs a Reconstructive Masked Autoencoder (RecMAE) capable of accurately reconstructing spectrum maps from sparse and temporally varying sensor data using a novel dual-mask mechanism. This approach significantly enhances the precision of reconstructed radio frequency (RF) power maps. In the second stage, the Multi-agent Diffusion Policy (MADP) method integrates diffusion-based reinforcement learning to optimize the trajectories of dynamic UAV sensors. By leveraging temporal-attention encoding, this method effectively manages spatial exploration and exploitation to minimize cumulative reconstruction errors. Extensive numerical experiments show that this integrated GenAI framework consistently surpasses traditional interpolation and deep learning methods, especially under sparse sensing conditions. The proposed trajectory planner substantially improves spectrum map accuracy, reconstruction stability, and sensor deployment efficiency in dynamically evolving low-altitude environments.

Semantic communication emphasizes the transmission of meaning rather than raw symbols. It offers a promising solution to alleviate network congestion and improve transmission efficiency. In this paper, we propose a wireless image communication framework that employs probability graphs as shared semantic knowledge base among distributed users. High-level image semantics are represented via scene graphs, and a two-stage compression algorithm is devised to remove predictable components based on learned conditional and co-occurrence probabilities. At the transmitter, the algorithm filters redundant relations and entity pairs, while at the receiver, semantic recovery leverages the same probability graphs to reconstruct omitted information. For further research, we also put forward a multi-round semantic compression algorithm with its theoretical performance analysis. Simulation results demonstrate that our semantic-aware scheme achieves superior transmission throughput and satiable semantic alignment, validating the efficacy of leveraging high-level semantics for image communication.

Quantum key distribution (QKD) has emerged as a promising solution for guaranteeing information-theoretic security. Inspired by this, a great amount of research effort has been recently put on designing and testing QKD systems as well as articulating preliminary application scenarios. However, due to the considerable high-cost of QKD equipment, a lack of QKD communication system design tools, wide deployment of such systems and networks is challenging. Motivated by this, this paper introduces a QKD communication system design tool. First we articulate key operation elements of the QKD, and explain the feasibility and applicability of coherent-one-way (COW) QKD solutions. Next, we focus on documenting the corresponding simulation framework as well as defining the key performance metrics, i.e., quantum bit error rate (QBER), and secrecy key rate. To verify the accuracy of the simulation framework, we design and deploy a real-world QKD setup. We perform extensive experiments for three deployments of diverse transmission distance in the presence or absence of a QKD eavesdropper. The results reveal an acceptable match between simulations and experiments rendering the simulation framework a suitable tool for QKD communication system design.

In this paper, we propose an effective blockchain-enabled information management framework, named Smart Blockchain-based Web 3.0 (SBW 3.0). Our framework aims to handle information within Web 3.0 efficiently, enhance data security and privacy, create new revenue streams, and encourage users to contribute valuable information to websites. To this end, SBW 3.0 employs blockchain technology and smart contracts to manage the decentralized data collection in Web 3.0. Moreover, we introduce a robust consensus mechanism grounded in Delegated Proof-of-Stake (DPoS) to reward user contributions. Furthermore, we develop a non-cooperative game model to examine user behavior in this context and conduct thorough analysis to prove the uniqueness of the Nash equilibrium in our proposed system. Through simulations, we evaluate the performance of SBW 3.0 and analyze the effects of various critical parameters on information contribution. Our results validate the theoretical analysis, showing that the proposed consensus mechanism successfully encourages nodes and users to provide more information, thus overcoming the current limitations of Web 3.0 regarding data decentralization and management.

The Industrial Internet of Things (IIoT) leverages Federated Learning (FL) for distributed model training while preserving data privacy, and meta-computing enhances FL by optimizing and integrating distributed computing resources, improving efficiency and scalability. Efficient IIoT operations require a trade-off between model quality and training latency. Consequently, a primary challenge of FL in IIoT is to optimize overall system performance by balancing model quality and training latency. This paper designs a satisfaction function that accounts for data size, Age of Information (AoI), and training latency for meta-computing. Additionally, the satisfaction function is incorporated into the utility function to incentivize IIoT nodes to participate in model training. We model the utility functions of servers and nodes as a two-stage Stackelberg game and employ a deep reinforcement learning approach to learn the Stackelberg equilibrium. This approach ensures balanced rewards and enhances the applicability of the incentive scheme for IIoT. Simulation results demonstrate that, under the same budget constraints, the proposed incentive scheme improves utility by at least 23.7% compared to existing FL schemes without compromising model accuracy.

Intelligent adaptive bitrate (ABR) schemes have been widely recognized for their excellent learning strategies. However, existing intelligent ABR methods have limitations, i.e., the lack of logical reasoning capability for video-aware symbolic representations leads to low sampling efficiency and fails to achieve the optimal performance of Bitrate Adaptation. We introduce NeuroBA, a learning-based approach to realize ABR using neuro-symbolic deep reinforcement learning. NeuroBA trains a neuro-symbolic deep network model without making any assumptions about the edge video scene and without relying on a predefined model. Instead, it enables bitrate decision-making under uncertainty and partial observability by knowledge-driven video quality perception in symbolic first-order logic. To enhance wireless signals, we have introduced Intelligent Reflecting Surface (IRS) technology to address this issue. By dynamically adjusting the phase shift of IRS, the throughput performance of wireless networks is significantly improved. Based on trace-driven and real-world experiments covering a variety of edge video scenarios, and network performance metrics, NeuroBA is compared with state-of-the-art ABR schemes, and NeuroBA exhibits superior performance, with an average QoE improvement of 16.58% (BOLA)-25.34% (Fugu). In particular, it outperforms existing baseline approaches even without pre-programmed models and network scenarios assumed for the edge network.

In the rapidly evolving Next-Generation Networking (NGN) era, the adoption of zero-trust architectures has become increasingly crucial to protect security. However, provisioning zero-trust services in NGNs poses significant challenges, primarily due to the environmental complexity and dynamics. Motivated by these challenges, this paper explores efficient zero-trust service provisioning using hierarchical micro-segmentations. Specifically, we model zero-trust networks via hierarchical graphs, thereby jointly considering the resource- and trust-level features to optimize service efficiency. We organize such zero-trust networks through micro-segmentations, which support granular zero-trust policies efficiently. To generate the optimal micro-segmentation, we present the Large Language Model-Enhanced Graph Diffusion (LEGD) algorithm, which leverages the diffusion process to realize a high-quality generation paradigm. Additionally, we utilize gradient ascent and Large Language Models (LLM) to enable LEGD to optimize the generation policy and understand complicated graphical features. Moreover, realizing the unique trustworthiness updates and service upgrades in zero-trust NGN, we further present LEGD-Adaptive Maintenance (LEGD-AM), providing an adaptive way to perform task-oriented fine-tuning on LEGD. Extensive experiments demonstrate that the proposed LEGD achieves 90% higher efficiency in provisioning services compared with other baselines. Moreover, the LEGD-AM can reduce the service outage time by over 50%.

Large Language Models (LLMs) can perform zero-shot learning on unseen tasks and few-shot learning on complex reasoning tasks. However, resource-limited mobile edge networks struggle to support long-context LLM serving for LLM agents during multi-round interactions with users. Unlike stateless computation offloading and static service offloading in edge computing, optimizing LLM serving at edge servers is challenging because LLMs continuously learn from context which raises accuracy, latency, and resource consumption dynamics. In this paper, we propose a joint model caching and inference offloading framework that utilizes test-time deep reinforcement learning (T2DRL) to optimize deployment and execution strategies for long-context LLM serving. In this framework, we analyze the performance convergence and design an optimization problem considering the utilization of context windows in LLMs. Furthermore, the T2DRL algorithm can learn in both the training phase and the testing phase to proactively manage cached models and service requests and adapt to context changes and usage patterns during execution. To further enhance resource allocation efficiency, we propose a double Dutch auction (DDA) mechanism, which dynamically aligns the marginal value of an additional reasoning path with the marginal cost of reasoning services. Finally, experimental results demonstrate that the T2DRL algorithm can reduce system costs by at least 30% compared to baselines while guaranteeing the performance of LLM agents in real-world perception and reasoning tasks.

Edge intelligence in space-air-ground integrated networks (SAGINs) can enable worldwide network coverage beyond geographical limitations for users to access ubiquitous and low-latency intelligence services. Facing global coverage and complex environments in SAGINs, edge intelligence can provision large language models (LLMs) agents for users via edge servers at ground base stations (BSs) or cloud data centers relayed by satellites. As LLMs with billions of parameters are pretrained on vast datasets, LLM agents have few-shot learning capabilities, e.g., chain-of-thought (CoT) prompting for complex tasks, which raises a new trade-off between resource consumption and performance in SAGINs. In this paper, we propose a joint caching and inference framework for edge intelligence to provision sustainable and ubiquitous LLM agents in SAGINs. We introduce “cached model-as-a-resource” for offering LLMs with limited context windows and propose a novel optimization framework, i.e., joint model caching and inference, to utilize cached model resources for provisioning LLM agent services along with communication, computing, and storage resources.We design “age of thought” (AoT) considering the CoT prompting of LLMs, and propose a least AoT cached model replacement algorithm for optimizing the provisioning cost. We propose a deep Q-network-based modified second-bid (DQMSB) auction to incentivize satellite/ground network operators in real-time, which can enhance allocation efficiency by 23% while guaranteeing strategy-proofness and being free from adverse selection.

Future wireless networks are anticipated to evolve by aerial communication platforms. Nonetheless, the operational lifespan and efficacy of transceivers such as unmanned aerial vehicle (UAVs) and Internet of Things (IoT) devices are strictly prohibited by their constrained onboard power sources. This paper focuses on an aerial network configuration where a UAV harvests solar power to serve energy-limited IoT devices through simultaneous wireless information and power transfer. In this setup, the UAV and the IoT devices, each are equipped with energy and data buffers. This system also benefits from rate splitting multiple access for efficient interference management. Upon optimizing the system efficacy, we formulate a long-term resource allocation problem to maximize the time-averaged energy efficiency. To address this stochastic and non-convex optimization problem, we propose a multi-stage solution strategy. Firstly, by leveraging Lyapunov optimization theory, we transform the long-term stochastic problem into an equivalent deterministic short-term form. Next, by recasting this equivalent problem into Markov decision process, we propose a resource allocation mechanism based on actor-critic hindsight experience replay (AC-HER), tailored to capture the problem dynamics and optimize its variables. Moreover, given the UAV high mobility and the system reconfigurations, we fortify the trained AC-HER model with meta-learning strategy, enhancing its adaptability to system variations. Simulations verified that the proposed resource allocation strategy considerably outperforms its counterparts.

With the increasing demand for artificial intelligence generated content (AIGC) services across diverse applications, AIGC service migration is essential to ensuring continuous service for mobile users in edge intelligence networks. However, AIGC service migration can lead to decreased inference accuracy due to the discarding of contextual memory. Furthermore, migrating large-scale AIGC models incurs high migration costs and latency. In this paper, we propose a context-aware AIGC service migration scheme to address the trade-off among inference accuracy, latency, and migration cost. Specifically, we focus on migrating historical AIGC context rather than large-scale AIGC models to achieve cost-efficient service provisioning. To improve service migration performance, we propose a Value of Context (VoC) metric to quantify the relevance and freshness of historical AIGC context. Based on the VoC, we formulate an optimization problem to jointly optimize inference accuracy, latency, and migration cost. To solve this problem, we develop a TransFormer-based Soft actor-critic algorithm for Context-aware AIGC service Migration (TFSCM) that leverages long-term dependencies in historical decisions for optimizing the migration process. Extensive experiments on real-world datasets demonstrate that the proposed TFSCM algorithm significantly enhances system performance compared to baseline solutions.

Mobile metaverses are envisioned as a transformative digital ecosystem that delivers immersive, intelligent, and ubiquitous services through mobile devices. Driven by Large Language Models (LLMs) and Vision-Language Models (VLMs), Artificial Intelligence (AI) agents hold the potential to empower the creation, maintenance, and evolution of mobile metaverses, enabling seamless human-machine interaction and dynamic service adaptation. Currently, AI agents are primarily built upon cloud-based LLMs and VLMs. However, several challenges hinder their efficient deployment, including high service latency and a risk of sensitive data leakage during perception and processing. In this paper, we develop an edge-cloud collaboration-based federated AI agent construction framework in mobile metaverses. Specifically, Edge Servers (ESs), as agent infrastructures, first create agent modules in a distributed manner. The cloud server then integrates these modules into AI agents and deploys them at the edge, thereby enabling low-latency AI agent services for users. Considering that ESs may exhibit dynamic levels of willingness to participate in federated AI agent construction, we design a two-period dynamic contract model to continuously incentivize ESs to participate in agent module creation, effectively addressing the dynamic information asymmetry between the cloud server and ESs. Furthermore, we propose an Enhanced Diffusion Model-based Soft Actor-Critic (EDMSAC) algorithm to effectively generate optimal dynamic contracts. In the algorithm, we apply dynamic structured pruning to DM-based actor networks to enhance denoising efficiency and policy learning performance. Simulation results demonstrate that the EDMSAC algorithm outperforms the DMSAC algorithm by up to 23% in optimal dynamic contract generation.

Federated split learning (FSL) has rapidly emerged as a promising paradigm for enabling ubiquitous intelligence in next-generation networks. However, current FSL approaches incur significant communication overhead and diminished training efficiency due to the frequent transmission of high-dimensional smashed data and gradients between devices and the base station. To address these issues, we propose a low-rank approximation (LoRA)-based FSL scheme, referred to as low-rank FSL. We analyze the convergence performance of low-rank FSL by considering the influence of LoRA rank on non-convex loss functions. To minimize a weighted sum of overall training latency and energy consumption in resource-constrained wireless networks, we formulate a long-term optimization problem by jointly optimizing computing frequency, power allocation, decoding order, LoRA rank, and split layer selection. An iterative optimization algorithm is then developed to solve this problem with low computational complexity. Numerical results demonstrate that our low-rank FSL reduces communication overhead by at least 300% while maintaining high learning performance. Moreover, our optimization algorithm achieves a low weighted cost in terms of training latency and energy consumption.

Reconfigurable intelligent surface (RIS) has been considered as an effective approach to achieve extremely large-scale MIMO (XL-MIMO). To mitigate the high-complexity of channel information acquisition brought by the large number of RIS elements, beam training has been applied to select an optimal beam from a predefined codebook for beamforming in large-scale RIS-aided systems. However, practical limitations of RIS, such as its macrocell structure and finite phase shifts, result in the overlap of codeword coverage, i.e., non-orthogonal beams, which degrades the accuracy of beam training. In this paper, we propose a self-correcting hierarchical beam training scheme, where we model the beam training as a sequential process based on a tailored long short-term memory network. Received powers of sequentially selected codewords layer by layer are used to construct quasi-orthogonality for optimizing the beam selection. Unlike traditional deep learning methods relying on sufficient data, which takes substantial overhead to collect, we design a diffusion-empowered generation module given the general data-constrained conditions. The generation module is capable of synthesizing codebook power profiles to enhance the beam training performance. Simulation results demonstrate that our proposed method outperforms existing beam training approaches in terms of accuracy and sum rate, even in the presence of dataset limitations.

In the rapidly advancing realm of wireless communication, device-to-device (D2D) technology, an emerging approach for data exchange and connectivity, has been attracting increasing attention. Unmanned Aerial Vehicles (UAVs) can act as air relays or base stations, and integrate isolated D2D clusters into a cohesive network fabric in outdoor environments. However, in complex terrain, the communication signals are subject to irregular attenuation, and the signal propagation attenuation of different frequency bands in the same terrain is inconsistent. It is challenging to utilize UAVs to coverage D2D terrestrial users in complex terrain. In this paper, we propose the UAVs relaying for bridging the terrestrial D2D networks assisted by multi-frequency radio maps. From the real-world topographical data, we generate multi-frequency radio maps, which represent the distortion of different frequency band signals by rich information about land layouts. Next, we focus on the air-to-ground D2D network topology and formulate it into an optimization problem. Then, we decompose it into two subproblems. The first subproblem pertains to the design of the ground network structure. We employ the D2D frequency band radio map to assess the communication quality between user pairs, and propose a measure of D2D closeness centrality to select ‘cellular users’ that can communicate directly to a UAV. The second subproblem involves the UAVs’ deployment and the frequency selection. We present a multi-frequency radio map improved k-means method, which has lower algorithm complexity than the traversal method by reducing the utilization of the radio maps. Simulations validate the proposed scheme, demonstrating that: 1. Multi-frequency radio maps can provide efficient gains with real-world complex topography; 2. The proposed network structure and algorithm outperform other existing approaches.

In this paper, we develop a tensor-based joint multi-dimensional (polarization, angle, and time delay) channel parameter estimation algorithm for single-input multiple-output (SIMO) communication systems equipped with an electromagnetic vector sensor (EMVS) linear array. By considering the EMVS array structure and multi-path propagation environment, the received signals at the base station (BS) are constructed into a third-order parallel factor (PARAFAC) tensor model. By decomposing the constructed tensor, we design a joint structured tensor decomposition algorithm (STDA) and bilinear alternating least squares (BALS) fitting algorithm using the Vandermonde structure of the array to estimate the factor matrices containing angles, polarization, and time delay. Based on the estimated factor matrices, we employ a closed-form algorithm to extract the two-dimensional direction of arrival (2D-DoA), polarization parameters, and time delay. In addition, to provide a quantitative assessment of the proposed algorithm’s performance, we calculate the Cramér-Rao bound (CRB) as a benchmark for comparison. Simulation results indicate that the proposed algorithm achieves superior estimation accuracy and is closer to the CRB compared with the existing tri-polarized algorithms.

This paper investigates a secure aerial reconfigurable intelligent surface (A-RIS) communication system, where user mobility, imperfect channel state information (CSI), and RIS phase errors induced by unmanned aerial vehicle (UAV) jitter significantly degrade performance. To address these challenges, we formulate a joint optimization problem for UAV trajectory, base station (BS) we propose abeamforming, and A-RIS beamforming to maximize the minimum secrecy energy efficiency (SEE), subject to constraints on user secrecy rates and UAV energy efficiency. To solve this highly non-convex problem, we propose a novel reinforcement learning framework termed IA-CSORL based on the twin-twin-delayed deep deterministic policy gradient (TTD3) architecture, which incorporates two novel modules. Specifically, we develop the phase-aware relativistic adaptive descent (PRAD) algorithm is proposed, which embeds the learning process into a conformal Hamiltonian system. By integrating gradient-based phase error correction and adaptive momentum adjustment, PRAD effectively counteracts phase noise and stabilizes training. Furthermore, we design an environment-state interactive attention (ESIA) mechanism to dynamically fuse UAV positioning and environmental features, enhancing state representation and deployment accuracy. Numerical results demonstrate that IA-CSORL significantly outperforms existing RL baselines in terms of both robustness and convergence performance. Moreover, IA-CSORL achieves superior beamforming accuracy under phase errors and CSI imperfections and provides a better trade-off between sum secrecy rate (SSR) and SEE, with performance gains becoming more significant as the number of RIS elements increases.

Decentralized Federated Learning (DFL) enables collaborative model training without central coordination. However, DFL faces challenges in dynamic networks, where existing methods struggle to balance consensus rate and communication efficiency, while overlooking practical issues such as topology variation. This paper presents Dynamic AirComp-enabled DFL (DA-DFL), a novel framework that integrates over-the-air computation (AirComp) with the BASE-GRAPH consensus algorithm for efficient DFL over dynamic topologies. The convergence analysis for DA-DFL under dynamic settings is conducted to reveal the influence of the consensus period and communication errors. We define communication overhead metrics, and jointly optimize transceiver beamformers and dynamic topologies. A topology matching algorithm is developed to reduce communication overhead by aligning logical and physical topologies. Experiments show significant gains of DA-DFL in communication efficiency, e.g., reducing communication links and distances by up to 42% and 50%, respectively, compared to benchmarks.

Unmanned aerial vehicles (UAVs) assisted communications have become one of the crucial approaches to enable the reliable and flexible data transmissions, particularly in ultra-reliable and low-latency scenarios, such as remote sensing, emergency response, and military long-range command transmission. In this paper, we investigate the secrecy performance of UAV-assisted short-packet transmission via non-orthogonal multiple access (NOMA), where a UAV serves as an aerial relay to forward mission-critical information from a base station to two remote users in the presence of a ground-based eavesdropper. Both the base station and UAV relay use beamforming for generating the artificial noise to disrupt the eavesdropping and enhance the security, and the UAV operates in half-duplex mode to meet resource constraints and avoid self-interference. The weighted effective secrecy rates of the two users are maximized by jointly optimizing the blocklength, transmission rate, power allocation coefficients, power-sharing factors and UAV position, which is shown to be non-convex and difficult to be solved directly. Accordingly, we decompose the problem into four sub-problems by applying the block coordinate descent (BCD) algorithm to maximize the weighted effective secrecy rate. Then, slack variables are introduced to further solve the sub-problems via successive convex approximation (SCA). Finally, simulation results are presented to demonstrate the effectiveness of the proposed scheme.

Cell-free (CF) massive multiple-input multiple-output (MIMO) has recently emerged as a highly promising technology for supporting future six-generation (6G) networks, owing to its unique ability to provide high data rates and reliable connectivity. However, a primary challenge in CF massive MIMO is severe inter-user interference, which is caused by densely located user equipments (UEs) and the presence of imperfect channel state information (CSI). Fortunately, the rate-splitting (RS) strategy offers significant benefits by enabling partially interference decoding, thereby greatly enhancing overall system performance. In this paper, we investigate the performance of uplink RS in CF massive MIMO systems. Considering the inevitable channel estimation errors caused by pilot contamination, we first derive a novel closed-form expression for characterizing spectral efficiency (SE). Moreover, we propose two innovative decoding strategies tailored to the 6G scenario, highlighting their role in enhancing the interference management capabilities of RS, while balancing decoding performance with computational complexity. To ensure successful decoding of each sub-message to the greatest extent possible, we devise an optimization-based power control scheme to maximize the minimum SE of the sub-messages, and propose a low-complexity scheme for comparative analysis. Additionally, we investigate the total energy efficiency (EE) of the system and propose a power control scheme for maximizing EE by exploiting fractional programming (FP) theory. Simulation results corroborate our theoretical expressions and demonstrate that both RS and the proposed power control schemes can significantly improve both SE and EE.

The space-terrestrial integrated network (STIN) is crucial for achieving ubiquitous connectivity in the 6G era. However, leveraging full potential of STIN is challenging due to the distinct characteristics and objectives of constituent networks. Inspired by symbiotic communication (SC), this paper proposes a service exchange-based symbiotic STIN system that optimizes objectives of different networks by exploiting their complementary features. Specifically, the ground network provides task offloading services to the space network, while the space network reciprocates with communication services. To minimize computation delay in the space network and maximize the energy efficiency (EE) of the ground network, we formulate a multi-objective optimization problem (MOOP) that jointly optimizes task offloading, resource allocation, and beamforming. We first transform the MOOP into a single-objective optimization problem (SOOP) via the ε-constraint method and then develop a successive convex approximation (SCA) algorithm to characterize its fundamental performance, which requires future state information. As obtaining such non-causal information is hard, we design a more practical multi-agent reinforcement learning (MARL) algorithm based on insights from the SCA. Besides, to address the challenges of storing multiple MARL policies for different EE-delay trade-offs, we develop a diffusion model-based behavior cloning (BC) algorithm to obtain a general policy suitable for varying trade-offs. Simulation results show that proposed algorithms outperform benchmarks and confirm that the proposed service exchange realizes a symbiotic STIN.

This paper presents a non-orthogonal retransmission framework for integrated satellite-terrestrial networks (ISTNs). This framework integrates hybrid automatic repeat request (HARQ) with incremental redundancy (HARQ-IR) and rate splitting multiple access (RSMA). HARQ-IR and RSMA are utilized for downlink retransmission and multi-user interference management, respectively, to address the requirements for extensive and highly reliable concurrent connections. Employing the inclusion-exclusion principle, we establish precise upper and lower bounds for the exact outage probability (OP), which function as approximations. We also examine the asymptotic OP, which yields significant insights and informs a partial HARQ-IR-RSMA scheme. We propose a joint common-private power allocation (JCPPA) algorithm based on alternating optimization (AO) to enhance the energy efficiency (EE) of the partial retransmission scheme while adhering to power and outage probability (OP) constraints. The non-convex problem is addressed effectively via asymptotic OP, which allows for the decomposition into common and private power optimization subproblems utilizing the Dinkelbach method. The common power optimization subproblem is convex and can be solved using the CVX toolbox. The private power optimization subproblem is addressed through variable substitution and the application of the Lagrangian dual algorithm. The numerical results indicate the accuracy and superiority of the proposed special scheme regarding outage performance and energy efficiency when compared to benchmarks.

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can be assembled in the air-ground integrated sensing and communication (ISAC) to significantly enhance the coverage and sensing performance. However, the near-field effect should be further considered with higher carrier frequency and increasing number of STAR-RIS elements. In this paper, we propose a STAR-RIS enabled air-ground near-field ISAC scheme, where an unmanned aerial vehicle (UAV) is deployed as the mobile base station (BS) and the semi-passive STAR-RIS architecture is adopted to alleviate the severe path loss. Specifically, we maximize the weighted sum rate to guarantee both the communication and sensing functionalities by jointly modifying the beamforming vectors at the BS, the reflection/transmission matrices of the STAR-RIS and, the hovering location of the UAV to well match the near-field effect, which is non-convex with coupled variables. To address this challenge, we first decompose the problem into three subproblems via block coordinate descent. Then, the semidefinite relaxation and successive convex approximation are leveraged to recast these subproblems into convex ones. Finally, we develop an alternating algorithm with low complexity to iteratively solve them. Simulation results are shown to demonstrate the superiority and validity of the proposed scheme.

With the rapid advancement of unmanned aerial vehicle (UAV) technology in recent years, cooperative communication in UAV networks (UAV-Ns) has made significant strides. However, the effectiveness of UAV-Ns cooperative communication relies heavily on the accurate estimation of channel state information (CSI). Unlike terrestrial networks, the mobility of UAV introduces time-varying channel characteristics, which can substantially affect the overall system capacity. Therefore, this paper investigates the system capacity of UAV-Ns while accounting for the effect of jitter characteristics of UAV. Specifically, we propose a cooperative transmission model utilizing multiple UAV base stations (UAV-BSs) to enhance the signal quality received by ground users through coordinated multi-point (CoMP) transmission. Additionally, we present a jittering channel model, derive the channel autocorrelation function, and assess the capacity of the proposed system. To deal with the jitter, we introduce a jitter compensation scheme based on long short-term memory networks to counteract the effects of UAV jitter and improve the accuracy of channel precoding. Numerical results demonstrate that our approach significantly enhances the communication performance of UAV-Ns under the impact of jitter. Compared to the traditional method, our scheme improves the estimation accuracy of the channel state by up to 3.8%, highlighting the potential of distributed UAV-BSs with CoMP to strengthen UAV-Ns communication.

Efficient video transmission is essential for seamless communication and collaboration within the visually-driven digital landscape. To achieve low latency and high-quality video transmission over a bandwidth-constrained noisy wireless channel, we propose a stable diffusion (SD)-based goal-oriented semantic communication (GSC) framework. In this framework, we first design a semantic encoder that effectively identify the keyframes from video and extract the relevant semantic information (SI) to reduce the transmission data size. We then develop a semantic decoder to reconstruct the keyframes from the received SI and further generate the full video from the reconstructed keyframes using frame interpolation to ensure high-quality reconstruction. Recognizing the impact of wireless channel noise on SI transmission, we also propose an SD-based denoiser for GSC (SD-GSC) condition on an instantaneous channel gain to remove the channel noise from the received noisy SI under a known channel. For scenarios with an unknown channel, we further propose a parallel SD denoiser for GSC (PSD-GSC) to jointly learn the distribution of channel gains and denoise the received SI. It is shown that, with the known channel, our proposed SD-GSC outperforms state-of-the-art ADJSCC, Latent-Diff DNSC, DeepWiVe and DVST, improving Peak Signal-to-Noise Ratio (PSNR) by 69%, 58%, 33% and 38%, reducing mean squared error (MSE) by 52%, 50%, 41% and 45%, and reducing Fréchet Video Distance (FVD) by 38%, 32%, 22% and 24%, respectively. With the unknown channel, our PSD-GSC achieves a 17% improvement in PSNR, a 29% reduction in MSE, and a 19% reduction in FVD compared to MMSE equalizer-enhanced SD-GSC. These significant performance improvements demonstrate the robustness and superiority of our proposed methods in enhancing video transmission quality and efficiency under various channel conditions.

This paper introduces a sensing-centric joint communication and millimeter-wave radar paradigm to facilitate collaboration among intelligent vehicles. We first propose a chirp waveform-based delay-Doppler quadrature amplitude modulation (DD-QAM) that modulates data across delay, Doppler, and amplitude dimensions. Building upon this modulation scheme, we derive its achievable rate to quantify the communication performance. We then introduce an extended Kalman filter-based scheme for four-dimensional (4D) parameter estimation in dynamic environments, enabling the active vehicles to accurately estimate orientation and tangential-velocity beyond traditional 4D radar systems. Furthermore, in terms of communication, we propose a dual-compensation-based demodulation and tracking scheme that allows the passive vehicles to effectively demodulate data without compromising their sensing functions. Simulation results underscore the feasibility and superior performance of our proposed methods, marking a significant advancement in the field of autonomous vehicles. Simulation codes are provided to reproduce the results in this paper: https://github.com/LiZhuoRan0.

This paper addresses the coalition formation and the resource allocation in a device-to-device assisted mobile edge computing network, where the user equipments (UEs) collaborate to share the communication bandwidth and the computation resources for the task offloading. Our goal is to minimize the task execution cost, which is defined as the weighted sum of energy consumption and processing delay. In particular, we model waiting time of UEs in a coalition for the task offloading and incorporate it in the task execution cost. Therefore, we propose a three-layer hierarchical optimization framework which integrates the convex optimization, the heuristic algorithm, and the coalition game theory. In particular, we propose a double weighted mutation genetic algorithm to enhance the convergence of the algorithm, which applies weighted mutations to the offloading leader and the offloading order in the coalition. Furthermore, the task execution costs in both middle and upper layers are analytically evaluated. Simulation results validate the effectiveness of our proposed algorithms in reducing the task execution costs and speeding up the convergence.

As a critical component of sixth-generation (6G) wireless networks, ultra-reliable and low-latency communication (URLLC) is expected to support real-time and reliable information exchange in low-altitude environments. However, achieving URLLC often incurs significant resource overhead, including increased bandwidth consumption, higher transmit power, and denser access point (AP) deployment, which pose significant challenges to both spectral efficiency (SE) and energy efficiency (EE). Besides, existing iterative optimization algorithms are computationally intensive and struggle to meet the latency requirements of URLLC. To address these challenges, we propose a hybrid aerial-terrestrial cell-free massive MIMO (CF-mMIMO) network to support diverse services, along with a channel prediction network and a deep mixture of experts (MoE) network for uplink optimization. First, we design a channel prediction network (CP-Net) to mitigate channel aging caused by high-mobility user equipment (UE). CP-Net employs three Transformer-based sub-networks for aged channel state information (CSI) prediction, while a channel quality-aware loss function is introduced to improve the prediction accuracy of weak links. Based on the predicted CSI, we develop a deep MoE network (MoE-Net) for power allocation comprising three expert models targeting different objectives. Then, we introduce a weighted gating network (WT-Net) to learn an efficient adaptive combination of expert outputs. The proposed framework better captures heterogeneous UE requirements and improves communication performance under URLLC constraints. Numerical results demonstrate the effectiveness of the proposed method.

Reconfigurable intelligent surface (RIS) has emerged as a pivotal technology for enhancing wireless networks. Compared to terrestrial RIS deployed on building facades, aerial RIS (ARIS) mounted on quadrotor unmanned aerial vehicle (UAV) offers superior flexibility and extended coverage. However, the inevitable tilt and altitude variations of a quadrotor UAV during flight may lead to severe beam misalignment, significantly degrading ARIS’s performance. To address this challenge, we propose an Euler angles-based ARIS control scheme that jointly optimizes the altitude and trajectory of the ARIS by leveraging the UAV’s dynamic model. Considering the constraints on ARIS flight energy consumption, flight safety, and the transmission power of a base station (BS), we jointly design the ARIS’s altitude, trajectory, phase shifts, and BS beamforming to maximize the system sum-rate. Due to the continuous control nature of ARIS flight and the strong coupling among variables, we formulate the problem as a Markov decision process and adopt a soft actor-critic algorithm with prioritized experience replay to learn efficient ARIS control policies. Based on the optimized ARIS configuration, we further employ the water-filling and bisection method to efficiently determine the optimal BS beamforming. Numerical results demonstrate that the proposed algorithm significantly outperforms benchmarks in both convergence and communication performance, achieving approximately 14.4% improvement in sum-rate. Moreover, in comparison to the fixed-horizontal ARIS scheme, the proposed scheme yields more adaptive trajectories and significantly mitigates performance degradation caused by ARIS tilting, demonstrating strong potential for practical ARIS deployment.

As the sixth generation wireless technology evolves, applications such as, holography, autonomous driving, and telemedicine require enhanced data rates, reliability, and spectral efficiency. Unmanned Aerial Vehicles (UAVs) have gained attention due to their flexible deployment, line-of-sight transmission, and dynamic adaptability. However, UAV-assisted communication encounters challenges stemming from UAV position deviations caused by environmental factors such as wind and turbulence, which degrade transmission reliability. To address these problems, we propose a Non-Orthogonal Multiple Access-based full-duplex UAV relay protocol to improve the system transmission rate. The protocol utilizes successive interference cancellation for signal separation and maximal ratio combining for signal enhancement. Considering UAV position uncertainty, we formulate a robust optimization problem for joint UAV position optimization and power allocation. By employing the Bernstein-type inequality, we transform the probabilistic constraints into the deterministic constraints and solve the problem using a block coordinate descent-based algorithm. Simulation results demonstrate that, compared to the benchmark schemes, the proposed strategy improves system throughput and exhibits enhanced robustness, particularly under significant UAV position deviations.

As a foundational technology for the sixth generation networks that integrates communication, sensing, computing, and intelligence, integrated sensing and communication (ISAC) surpasses conventional isolated system designs across multiple performance dimensions. Given its superior interference management capability, non-orthogonal multiple access (NOMA) presents significant potential for integration into ISAC systems. To this end, this paper establishes a unified NOMA-ISAC framework that concurrently incorporates residual hardware impairments, channel estimation errors, and imperfect successive interference cancellation (SIC). Within this framework, we propose two distinct SIC designs tailored for different operational priorities: a communication-centric design (CCD) and a sensing-centric design (SCD), thereby introducing SIC ordering as a new dimension for managing the sensing-communication trade-off. For both proposed designs, we derive analytical expressions encompassing exact and asymptotic lower bounds of outage probabilities, ergodic communication rates for users, as well as probability of detection (PoD), probability of false alarm, and sensing sum rate for the base station. These analytical results provide a theoretical foundation for optimizing critical system parameters, such as power allocation and beamforming design. Our analysis reveals the synergistic effect of these impairments, leading to a simultaneous error floor in both communication and sensing performance. Notably, the proposed SIC ordering enables substantial performance gains in the prioritized domain: the CCD scheme improves ECRs by over 40%, whereas the SCD scheme enhances target PoD by more than 25%, under practical impairment conditions.

The combination of Integrated Sensing and Communication (ISAC) and Mobile Edge Computing (MEC) enables devices to simultaneously sense the environment and offload data to the base stations (BS) for intelligent processing, thereby reducing local computational burdens. However, transmitting raw sensing data from ISAC devices to the BS often incurs substantial fronthaul overhead and latency. This paper investigates a three-tier collaborative inference framework enabled by Integrated Sensing, Communication, and Computing (ISCC), where cloud servers, MEC servers, and ISAC devices cooperatively execute different segments of a pre-trained deep neural network (DNN) for intelligent sensing. By offloading intermediate DNN features, the proposed framework can significantly reduce fronthaul transmission load. Furthermore, multiple-input multiple-output (MIMO) technology is employed to enhance both sensing quality and offloading efficiency. To minimize the overall sensing task inference latency across all ISAC devices, we jointly optimize the DNN partitioning strategy, ISAC beamforming, and computational resource allocation at the MEC servers and ISAC devices, subject to sensing beampattern constraints. We also propose an efficient two-layer optimization algorithm. In the inner layer, we derive closed-form solutions for computational resource allocation using the Karush-Kuhn-Tucker conditions. Moreover, we design the ISAC beamforming vectors via an iterative method based on the majorization–minimization and weighted minimum mean square error techniques. In the outer layer, we develop a cross-entropy-based probabilistic learning algorithm to determine an optimal DNN partitioning strategy. Simulation results demonstrate that the proposed framework substantially outperforms existing two-tier schemes in inference latency.

Low altitude uncrewed aerial vehicles (UAVs) are expected to facilitate the development of aerial-ground integrated intelligent transportation systems and unlocking the potential of the emerging low-altitude economy. However, several critical challenges persist, including the dynamic optimization of network resources and UAV trajectories, limited UAV endurance, and imperfect channel state information (CSI). In this paper, we offer new insights into low-altitude economy networking by exploring intelligent UAV-assisted vehicle-to-everything communication strategies aligned with UAV energy efficiency. Particularly, we formulate an optimization problem of joint channel allocation, power control, and flight altitude adjustment in UAV-assisted vehicular networks. Taking CSI feedback delay into account, our objective is to maximize the vehicle-to-UAV communication sum rate while satisfying the UAV's long-term energy constraint. To this end, we first leverage Lyapunov optimization to decompose the original long-term problem into a series of per-slot deterministic subproblems. We then propose a diffusion-based deep deterministic policy gradient (D3PG) algorithm, which innovatively integrates diffusion models to determine optimal channel allocation, power control, and flight altitude adjustment decisions. Through extensive simulations using real-world vehicle mobility traces, we demonstrate the superior performance of the proposed D3PG algorithm compared to existing benchmark solutions.

The rapid advancement of 5G networks has significantly increased the demand for high throughput and low latency, particularly for enhanced Mobile Broadband (eMBB) services. Optimizing user rates in large-scale base station (BS) collaborative scenarios is crucial, ensuring high throughput and low energy consumption while meeting the needs of users. The optimization process faces two key challenges: how to efficiently explore and utilize the vast action space for collaborative decision-making in large-scale networks with numerous BSs, and how to ensure optimal decision-making across numerous parameters while satisfying constraints. To tackle these challenges, we propose a novel solution that integrates a generative AI-powered Digital Twin platform with a multi-agent reinforcement learning (MARL) decision algorithm. An important tool is the high-fidelity DT-SimNet platform, enabling seamless integration with AI optimizers. Moreover, we propose a novel algorithm called Safe Hierarchical Multi-Agent Proximal Policy Optimization with Adaptive Prediction mechanism (Safe HMAPPO-AP). This algorithm integrates Safe MARL to ensure decision-making remains within constraint boundaries and incorporates a hierarchical structure to decompose the action space. Moreover, it leverages Graph Neural Networks (GNNs) for efficient feature extraction and employs the Adaptive Prediction mechanism to accelerate learning and improve network performance. Comprehensive experiments using the DT-SimNet platform demonstrate the superior performance of the proposed algorithm compared to competing methods. Within the target area, Safe HMAPPO-AP achieved a 6.73% improvement in average throughput for regular users and an 11.48% increase in system utility, while meeting demands of newly added eMBB users.

This paper proposes a promising framework of multi-functional service incorporating sensing targets (STs), information receivers (IRs), and energy receivers (ERs) in an active reconfigurable intelligent surface (RIS)-aided integrated sensing, communication, and power transfer (ISCPT) system. In the proposed system, we aim to maximize the weighted sum of the received radar signal-to-interference-plus-noise-ratio (SINR) by jointly optimizing the transmit beamforming at the multi-functional base station (MFBS), the coefficients of active RIS, and the radar receive filter coefficients. Meanwhile, the constraints of the SINR of IRs, energy harvesting (EH) requirements of ERs, the power budget for the MFBS and active RIS, and the amplification gain should be satisfied. To guarantee the generality of formulated problems, we further incorporate the self-interference effects of echo signals, multi-target echo interference, simultaneous detection of multiple STs, and a nonlinear EH model into the generalized system model. Due to the presence of echo interference and multi-target echo interference, the MFBS transmits the dedicated sensing signal with the communication to enhance the sensing performance. The formulated problem is tackled by developing an efficient alternating optimization (AO) algorithm combined with fractional programming (FP) and majorization-minimization (MM) techniques. Finally, the numerical results reveal the impact of system parameters on the sensing performance, the trade-off relationship between multiple functionalities, and the deployment strategy of RIS. The main findings are as follows: 1) Active RIS is remarkably superior to passive RIS for ISCPT systems, especially for closer to the receivers with a 40 dB performance gain. 2) Comparatively, the radar sensing SINR is more sensitive to the number of active RIS units, while the SINR of IRs is more sensitive to the number of antennas at the base station. These results demonstrate that the proposed system holds the potential for practical deployment.

Recently, an emerging flexible-antenna technology, termed pinching antennas, has attracted growing academic interest. By inserting discrete dielectric materials, pinching antennas can be activated at arbitrary points along waveguides, allowing for flexible customization of channel conditions. This paper investigates a multi-waveguide pinching-antenna integrated sensing and communications (ISAC) system, where transmit pinching antennas (TPAs) and receive pinching antennas (RPAs) coordinate to simultaneously detect one potential target and serve one downlink user. We formulate a communication rate maximization problem subject to radar signal-to-noise ratio (SNR) requirement, transmit power budget, and the allowable movement region of the TPAs, by jointly optimizing TPA locations and transmit beamforming design. To address the non-convexity of the problem, we propose a novel fine-tuning approximation method to reformulate it into a tractable form, followed by a successive convex approximation (SCA)-based algorithm to obtain the solution efficiently. Furthermore, we derive the closed-form optimal solution for a special multi-waveguide case involving a single TPA. Extensive simulations validate both the system design and the proposed algorithm. Results show that the proposed method achieves near-optimal performance compared with the computational-intensive exhaustive search-based benchmark, and pinching-antenna ISAC systems exhibit a distinct communication-sensing trade-off compared with conventional systems.

Integrated Sensing and Communication (ISAC) can assist Uncrewed Aerial Vehicle (UAV) secure communications by acquiring information about eavesdroppers. However, existing studies have not systematically investigated ISAC beamforming for simultaneously sensing the channel information of ground eavesdroppers, jamming eavesdropping links, and communicating with users, which poses significant challenges in ensuring both sensing accuracy and communication confidentiality. To address this issue, we propose a UAV-ISAC secure communication algorithm to maximize average secrecy rate by jointly optimizing communication and sensing beamforming, user scheduling, sensing time allocation, and UAV trajectory. We address the formulated NP-hard problem by decomposed it into three subproblems. We first relax binary user scheduling and sensing time allocation by a penalty-based successive convex approximation approach. The UAV trajectory is then iteratively optimized while beamforming is designed using semidefinite relaxation, with matrix lifting applied to handle the rank-one constraint. A triple-layer iterative algorithm is constructed by integrating these steps to achieve a suboptimal solution. Numerical experiment results and theoretical analysis validate the superiority of the proposed algorithm in terms of average secrecy rate, convergence and computational complexity.

Wireless Human-Machine Collaboration (WHMC) represents a critical advancement for Industry 5.0, enabling seamless interaction between humans and machines across geographically distributed systems. As the WHMC systems become increasingly important for achieving complex collaborative control tasks, ensuring their stability is essential for practical deployment and long-term operation. Stability analysis certifies how the closed-loop system will behave under model randomness, which is essential for systems operating with wireless communications. However, the fundamental stability analysis of the WHMC systems remains an unexplored challenge due to the intricate interplay between the stochastic nature of wireless communications, dynamic human operations, and the inherent complexities of control system dynamics. This paper establishes a fundamental WHMC model incorporating dual wireless loops for machine and human control. Our framework accounts for practical factors such as short-packet transmissions, fading channels, and advanced HARQ schemes. We model human control lag as a Markov process, which is crucial for capturing the stochastic nature of human interactions. Building on this model, we propose a stochastic cycle-cost-based approach to derive a stability condition for the WHMC system, expressed in terms of wireless channel statistics, human dynamics, and control parameters. Our findings are validated through extensive numerical simulations and a proof-of-concept experiment, where we developed and tested a novel wireless collaborative cart-pole control system. The results confirm the effectiveness of our approach and provide a robust framework for future research on WHMC systems in more complex environments.

The rapid proliferation of the Internet of Things has given rise to a multitude of real-time applications, which pose significant computing challenges for resource-constrained users. Air-ground collaborative mobile edge computing (AGMEC) emerges as an innovative solution, integrating aerial and terrestrial computing paradigms to provide flexible, efficient services that significantly enhance data processing capabilities. This paper focuses on the freshness of task data in AGMEC networks, characterized by the emerging metric of age of information (AoI). Due to limited spectrum resources and network coverage gaps, we introduce non-orthogonal multiple access (NOMA) and active reconfigurable intelligent surface (RIS) technologies to facilitate efficient task offloading. We formulate a joint optimization problem of uncrewed aerial vehicle trajectory, active RIS beamforming, and task offloading strategy to minimize the network’s average AoI under multidimensional constraints. Considering the non-convex nature and the dynamic characteristics of the AGMEC environment, we develop an action adjuster-based deep deterministic policy gradient (AADDPG) algorithm. The innovative design of the action adjuster enables the algorithm to not only achieve efficient processing of hybrid action spaces but also effectively protect UAV battery performance. Simulation results demonstrate that the proposed AADDPG algorithm significantly improves AoI performance compared to other benchmark algorithms. Additionally, the results corroborate the efficacy of both NOMA and active RIS in minimizing AoI for AGMEC networks.

Integrated satellite-terrestrial networks (ISTNs) have played a crucial role in next-generation wireless systems. In this paper, we introduce partial non-orthogonal multiple access (p-NOMA) into ISTNs for downlink transmission, focusing on the system performance of satellite user equipments (UEs) and terrestrial UEs with co-channel interference and imperfect successive interference cancellation. We employ the Poisson point process to model the spatial distribution of the ground base stations, with Shadowed-Rician fading for satellite-terrestrial links and Rayleigh fading for terrestrial links. The closed-form expressions for the outage probability and average achievable rate of both satellite UEs and terrestrial UEs are derived. Additionally, we analyze the performance of the p-NOMA scheme and present the comparisons with non-orthogonal multiple access (NOMA) and orthogonal multiple access schemes. We validate the analytical results through simulations, confirming that p-NOMA outperforms NOMA in terms of both outage probability and average achievable rate. Moreover, we investigate the impact of p-NOMA parameters on the average achievable rate in the terrestrial network, providing insights for optimizing system performance.

Millimeter-wave (mmWave) communications, coupled with directional antenna-based Flying Ad-Hoc Networks (FANETs), have received considerable attention for their potential to provide high-speed, low-latency communications for a variety of applications. However, the high mobility of Unmanned Aerial Vehicles (UAVs) in FANETs leads to dynamic changes in relative positions, resulting in frequent link failures. Effective link maintenance in such networks has become a critical challenge. This paper addresses this issue by developing mathematical models of link disconnections in directional antenna-based FANETs. Specifically, we derive the probability density functions for link disconnections due to distance and angular misalignment in closed-form expressions. Based on these prediction models, we propose the Adaptive Link Breakage Prediction with Directionality (ALBP-D) method, which exploits the high directional gain of directional antennas to extend link lifetime and improve network performance. We compare ALBP-D with two baseline methods, the Periodic Link Maintenance (PLM) method and the Residual Path Lifetime (RPL) method, through extensive simulations. The results show that ALBP-D achieves superior performance, with approximately a 10-fold improvement in both link lifetime and network connectivity duration compared to the baseline methods. In addition, ALBP-D exhibits significant improvements in maintenance overhead efficiency, especially at higher max range adjustment count, achieving a 5 to 7-fold improvement over baseline methods. These results highlight the effectiveness of ALBP-D in directional antenna-based FANETs. We also implemented a prototype system consisting of a directional antenna node and an omnidirectional antenna node using realistic UAV trajectory data. Experimental results show that the prediction models agree well with the real link disconnection data, confirming the practical feasibility and accuracy of the proposed method.

Jamming attacks pose a significant threat to the security of air-ground communications, where the challenge becomes more severe when involving multiple unmanned aerial vehicles (UAVs) incurring complex interference. To address this issue, this paper proposes a graph attention-based reinforcement learning strategy for anti-jamming UAV communications. Specifically, we consider the multi-UAV transmission and deployment in the presence of jamming attacks. Then, we formulate a zero-sum game with the legitimate side and adversary to maximize and minimize the overall transmission rate, respectively. Given the complicated structure of the game, we decompose it into two layers, tackled in a hierarchical learning framework. Particularly, the inner layer addresses the legitimate beamforming, for which we establish the graph attention network (GAT) to track the complicated interference and jamming relationship based on the graph representation of the UAV network. The outer layer address the legitimate UAV deployment and adversarial jamming policy, which is reinterpreted in a multi-agent deep reinforcement learning framework to obtain the strategies of both sides. The inner GAT is then nested within the outer multi-agent learning framework in a hierarchical manner to approximate the equilibrium of the original game model. Simulation results demonstrate the convergence and the performance superiority of the proposed learning scheme in terms of anti-jamming transmission rate. Also, the results exhibit significant generalization capability to cover different network configurations and parameters with reliable communication performance.

The flexible deployment of Unmanned Aerial Vehicle (UAV) swarms holds significant potential for low-altitude economy, but their communication security is severely threatened by malicious jamming. Generally, existing anti-jamming methods often overlook multi-user interference in swarm scenarios and fail to exploit the full potential of Intelligent Reflecting Surface (IRS) architectures. To solve the above challenges, we propose for the first time an anti-jamming framework for UAV swarm communications assisted by a Hybrid-IRS-assisted UAV (H-UAV). We jointly optimize the H-UAV’s trajectory, the hybrid IRS’s beamforming and active/passive element allocation of IRSs, and Non-Orthogonal Multiple Access (NOMA) communication strategy under imperfect jammer Channel State Information (CSI), to maximize average system transmission rate while minimizing communication energy consumption. To handle the formulated highly-coupled non-convex problem, we decompose it into three sub-problems. Specifically, we employ Successive Convex Approximation (SCA) to optimize the H-UAV’s trajectories. The IRS beamforming and element allocation are then transformed into a semi-definite programming problem by a designed penalty-based approach. Finally, the NOMA decoding order and power allocation are optimized via a dynamic ordering scheme and an SCA-based algorithm. Compared to existing representative schemes, the proposed framework can achieve higher average transmission rates and lower energy consumption.

Over-the-Air Federated Edge Learning (OTA-FEEL) has emerged as a promising paradigm for collaborative AI model training across heterogeneous edge devices. Despite its advantages in communication efficiency and privacy preservation, OTA-FEEL faces critical challenges, including channel fading, energy constraints of edge devices, and non-i.i.d data distributions. This paper is the first to investigate a joint impact of local data distribution heterogeneity and transmission distortion on model convergence of OTA-FEEL. Accordingly, we analyze the gap between global expected and optimal losses, and formulate the gap minimization problem under long-term energy consumption constraints. To solve this problem, we propose an energy-aware alternating resource allocation algorithm based on Lyapunov optimization framework, jointly addressing transmit power control and device sampling rate selection. Specifically, we transform the non-convex problem based on inverse convex optimization. Then, we employ first-order Taylor expansion to linearize the non-convex constraint, and also develop an iterative framework based on block coordinate descent and successive convex approximation to enable rapid convergence. Extensive simulations under three types of non-i.i.d data distributions validate the effectiveness of the proposed EARA algorithm, which consistently outperforms representative algorithms by achieving test accuracy approaching the theoretical upper bound, while maintaining significantly low energy consumption.

While Internet of Vehicles (IoV) networks enhance road safety and driving intelligence through collaborative sensing, reliable data sharing remains a critical challenge due to severe inter-vehicle interference and scarce wireless bandwidth. Conventional orthogonal multiple access often imposes bottlenecks in multiuser semantic communication by failing to accommodate the high heterogeneity of semantic representations among different users. To overcome this, we propose a new context-aware hybrid access framework for Cooperative Semantic Communication (CoSC), which strategically aligns access modes with semantic attributes to maximize fusion efficiency. The fundamental design of CoSC decouples transmission by broadcasting critical semantic information via reliable orthogonal modes to serve as semantic context, while fusion features are aggregated through high-capacity concurrent modes. Within this framework, we first design a context-attentive cooperative channel encoder to align semantic features from different vehicles under the shared context. Next, a semantic fusion-oriented precoding algorithm resolves potential feature conflicts in concurrent channels. Finally, to recover semantic signals from hybrid access modes with a unified receiver, we design a Bayesian-guided score-diffusion algorithm to reconstruct semantic information adaptively from heterogeneous signals. Extensive simulations show that CoSC supports scalable multiuser fusion, yielding a 34.2% improvement in average precision on the OPV2V dataset relative to state-of-the-art methods.

Combining integrated sensing and communication (ISAC) and an unmanned aerial vehicle (UAV) can not only save the wireless resource but also enhance the air-ground coverage. However, the high-quality air-ground link of ISAC network is more prone to exposure, and its security is challenging. In this paper, we design a covert air-ground transmission scheme for ISAC, where the sensing signal can be utilized as a mask to disrupt the detection of communication by Willie. Since it is difficult to obtain the accurate knowledge about Willie’s location, we employ the norm-bounded model to describe the uncertainty of location at Willie. To further enhance the covertness, a full-duplex (FD) UAV user is considered to receive the covert signal while transmitting the artificial jamming to confuse Willie. We first calculate the minimum detection error probability (MDEP) by deriving the optimal detection threshold, and we obtain the analytic expression of average MDEP. Then, the covert transmission rate is maximized by controlling beamforming vectors and the UAV trajactory while satisfying the target detection constraint, the covertness constraint as well as the transmit power constraint, which can be resolved by an alternating optimization algorithm. Finally, we present simulation results to verify that the proposed scheme with the FD jamming can better guarantee the covertness of air-ground ISAC.

Cooperative cognitive radio (CR) networks can enable secondary users (SUs) to access the spectrum without disrupting the transmission of primary users (PUs), which brings a series of security challenges despite the significant increase in spectrum efficiency. In this paper, we propose a novel unmanned aerial vehicle (UAV) assisted covert transmission scheme for cooperative CR networks, where a UAV as the secondary transmitter can send its covert signal to a secondary receiver while ensuring the quality of service for the PU. To achieve the covert transmission of SU, the PU’s signal is used as a beneficial interference to disturb the detection of wardens. We first derive the minimum detection error probability and Kullback-Leibler divergence under the finite blocklength constraint. Then, the average effective throughput maximization problem under the probabilistic line-of-sight channel is established by jointly optimizing the UAV’s transmit power and trajectory. Finally, numerical results verifies that the UAV relay in the proposed scheme can not only assist in the information transmission of PU but also achieve the covert communication for the secondary network in the presence of multiple wardens.

In this paper, we investigate the low-complexity distributed combining scheme design for near-field cell-free extremely large-scale multiple-input-multiple-output (CF XL-MIMO) systems. Firstly, we construct the uplink spectral efficiency (SE) performance analysis framework for CF XL-MIMO systems over centralized and distributed processing schemes. Notably, we derive the centralized minimum mean-square error (CMMSE) and local minimum mean-square error (LMMSE) combining schemes over arbitrary channel estimators. Then, focusing on the CMMSE and LMMSE combining schemes, we propose five low-complexity distributed combining schemes based on the matrix approximation methodology or the symmetric successive over relaxation (SSOR) algorithm. More specifically, we propose two matrix approximation methodology-aided combining schemes: Global Statistics & Local Instantaneous information-based MMSE (GSLI-MMSE) and Statistics matrix Inversion-based LMMSE (SI-LMMSE). These two schemes are derived by approximating the global instantaneous information in the CMMSE combining and the local instantaneous information in the LMMSE combining with the global and local statistics information by asymptotic analysis and matrix expectation approximation, respectively. Moreover, by applying the low-complexity SSOR algorithm to iteratively solve the matrix inversion in the LMMSE combining, we derive three distributed SSOR-based LMMSE combining schemes, distinguished from the applied information and initial values.

As edge applications demand real-time processing with limited bandwidth and energy, traditional communication systems face challenges to meet performance requirements due to the centralized architecture and redundant data transmission. To address these challenges, we propose a UAV-assisted semantic edge computing network that leverages UAV mobility and semantic communication. We formulate a joint optimization problem involving UAV trajectory, data allocation, and semantic extraction to maximize the semantic processing rate. To solve this problem, we develop a hybrid deep deterministic policy gradient (H-DDPG) algorithm that integrates deep reinforcement learning (DRL) with convex optimization via block coordinate descent (BCD), thereby enabling efficient joint decision-making across tightly coupled variables. Furthermore, we propose a hybrid diffusion deep deterministic policy gradient (H-D3PG) algorithm, which incorporates denoising diffusion models into the DRL framework. By addressing the limited adaptability of deterministic strategies, this design enhances policy expressiveness and stability. As a result, the algorithm enables adaptive trajectory control under time-varying semantic tasks and wireless channel conditions in UAV-assisted edge networks. Simulations show that H-D3PG improves the semantic processing rate by up to 38.8% while reducing energy consumption compared to Raw Data Transmission.

As a paradigm shift towards pervasive intelligence, semantic communication (SemCom) has shown great potentials to improve communication efficiency and provide user-centric services by delivering task-oriented semantic meanings. However, the exponential growth in connected devices, data volumes, and communication demands presents significant challenges for practical SemCom design, particularly in resource-constrained wireless networks. In this work, we propose a task-agnostic semantic communication (TASC) framework capable of supporting multimodal data across diverse tasks. To investigate the interplay between communication and intelligent tasks from an information-theoretic perspective, we introduce a distributed multimodal information bottleneck (DMIB) principle, which enables the extraction of minimal sufficient unimodal and multimodal representations by eliminating redundant information while preserving task-relevant semantics. To further reduce the communication overhead, we develop an adaptive semantic feature transmission method under dynamic channel conditions. Then, TASC is trained based on federated meta-learning (FML) to learn a well-initialized model for rapid adaptation and generalization. To gain deep insights, we conduct theoretical analysis and devise resource management to accelerate convergence while minimizing the training latency and energy cost. Moreover, we develop a joint user selection and resource allocation algorithm to address the non-convex problem with theoretical guarantees. Extensive simulation results validate the effectiveness and superiority of the proposed TASC compared to baselines.

Massive multiple-input multiple-output (MIMO) array systems are a cornerstone technology for beyond fifth-generation (B5G) and sixth-generation (6G) wireless communications. This paper proposes a novel algorithm for the joint estimation of direction-of-departure (DOD) and direction-of-arrival (DOA) in massive MIMO systems under unknown gain-phase errors. The proposed method first exploits a normalized rotational invariance property to extract the relative amplitude-phase difference vectors between adjacent antenna elements. By incorporating the prior knowledge that the transmitter and receiver phase errors follow a zero-mean distribution, we formulate two decoupled cost functions to enable joint DOD and DOA estimation. We then obtain that the corresponding angular parameters efficiently through low-complexity spectral searches. Notably, the proposed method requires only one well-calibrated transmitter and one well-calibrated receiver, thereby substantially reducing the calibration effort compared with existing approaches. The gain errors are directly estimated from the amplitude-phase difference vectors, while the phase error vectors are reconstructed using the estimated DOD and DOA values. The proposed framework accommodates general conformal transceiver array geometries and effectively mitigates error accumulation in gain-phase calibration. Simulation results verify that the proposed algorithm achieves superior angular estimation accuracy and calibration precision compared with state-of-the-art techniques.

The cell-free integrated sensing and communication (CF-ISAC) system, which effectively mitigates intra-cell interference and provides precise sensing accuracy, is a promising technology for future 6G networks. However, to fully capitalize on the potential of CF-ISAC, accurate time synchronization (TS) between access points (APs) is critical. Due to the limitations of current synchronization technologies, TS errors have become a significant challenge in the development of the CF-ISAC system. In this paper, we propose a novel CF-ISAC architecture based on movable antennas (MAs), which exploits spatial diversity to enhance communication rates, maintain sensing accuracy, and reduce the impact of TS errors. We formulate a worst-case sensing accuracy optimization problem for TS errors to address this challenge, deriving the worst-case Cramér-Rao lower bound (CRLB). Subsequently, we develop a joint optimization framework for AP beamforming and MA positions to satisfy communication rate constraints while improving sensing accuracy. A robust optimization framework is designed for the highly complex and non-convex problem. Specifically, we employ manifold optimization (MO) to solve the worst-case sensing accuracy optimization problem. Then, we propose an MA-enabled meta-reinforcement learning (MA-MetaRL) to design optimization variables while satisfying constraints on MA positions, communication rate, and transmit power, thereby improving sensing accuracy. The simulation results demonstrate that the proposed robust optimization algorithm significantly improves the accuracy of the detection and is strong against TS errors. Moreover, compared to conventional fixed position antenna (FPA) technologies, the proposed MA-aided CF-ISAC architecture achieves higher system capacity, thus validating its effectiveness.

In this paper, we propose a general energy efficiency (EE) optimization framework for the hybrid analog-digital transceivers design in multi-hop communication systems. The analog and digital beamforming matrices are jointly optimized considering two kinds of practical power constraint models, i.e., sum power with box eigenvalue constraints (SPBECs) and multiple weighted power constraints (MWPCs), and unit-modulus constraints on analog beamforming matrices. For both the SPBECs and MWPCs cases, to tackle the challenging problem involving highly-coupled variables, an effective decoupling approach is first proposed. Specifically, a set of auxiliary variables are introduced to equivalently transform the original problem into a decoupled form with respect to the variables of each node. Then, for each node, we propose an efficient two-stage analog and digital beamforming optimization algorithm. To be specific, we optimize the analog beamforming matrices in the first stage by jointly exploiting the matrix-monotonic optimization framework and channel-alignment strategy. Then, we optimize the digital beamforming matrices in the second stage based on the multi-node water-filling methodology. Furthermore, in order to compute the parameters involved in the multi-node water-filling solutions for the SPBECs case, we propose two novel strategies, i.e., the Dinkelbach based strategy and the per-node penalty based strategy, which derive the parameters in closed-forms and offer clear physical interpretations. Moreover, the per-node penalty based strategy is effectively extended to the MWPCs case by additionally employing the Lagrangian duality theory. Simulation results demonstrate the superior performance and high efficiency of our proposed algorithms.

Movable antenna (MA) has emerged as a promising technology for enhancing communication performance over conventional fixed position antenna (FPA) by exploiting spatial channel variations. In this paper, we propose a general energy efficiency (EE) optimization framework for the MA-aided multi-user multiple-input multiple-output (MU-MIMO) downlink communications. We jointly optimize the precoding matrices and the positions of transmit and receive MAs considering two different types of power constraint models, i.e., the sum power constraint (SPC) and multiple weighted power constraints (MWPCs), and various physical constraints on MA positions. In both the SPC case and the MWPCs case, we optimize the MA positions by jointly employing the weighted minimum mean square error (WMMSE) and successive convex approximation (SCA) methodologies. As for the precoding matrices optimization, by exploiting the uplink-downlink duality of MU-MIMO systems, we transform the downlink EE optimization into their virtual uplink EE optimization counterparts. Then, we derive the optimal structures of the precoding matrices, where the involved optimal power allocations take the multi-user water-filling solutions. To compute the parameters of the multi-user water-filling solutions, by taking advantage of the underlying algebraic monotonicity of the problem, we propose three novel design strategies, i.e., the direct Dinkelbach based design, the modified Dinkelbach based design, and the bound-ware penalty based design. In contrast to conventional fractional programming (FP) based EE optimization methods, the proposed algorithms offer significantly lower computational complexities and explicit physical insights. Moreover, the simulation results demonstrate the superior performance and high efficiency of our proposed EE optimization algorithms.

The combination of reconfigurable intelligent surface (RIS) and integrated sensing and communication (ISAC) can improve the resource utilization in non-line-of-sight scenarios. To sense the target with high accuracy, it is necessary to directionally reflect the sensing signal toward the sensing target via the RIS, improving the sensing performance. However, enhancing signal quality may increase the risk of information leakage when the sensing target is the warden. Against this background, we investigate a covert transmission problem in an RIS assisted ISAC system. Specifically, we obtain a tractable form of covertness constraint in terms of minimum detection error probability via the optimal detection threshold. Then, we maximize the sum covert transmission rate by jointly optimizing the beamforming of confidential signal and jamming signal as well as the RIS’s phase shift, while ensuring the reliability, covertness and sensing constraints. Owing to the effectiveness of the deep reinforcement learning algorithm in processing high-dimensional data and making intelligent decision, we propose a twins-deep deterministic policy gradient-based joint covert beamforming and the phase shift of RIS optimization (TD3-CBP) algorithm to solve the above non-convex problem. Finally, simulation results demonstrate the effectiveness of the proposed TD3-CBP algorithm in the covertness performance, achieving an average of 16.1 % higher sum covert transmission rate than the benchmark algorithms.

Accurate Channel State Information is prerequisite for intelligent sensing and ubiquitous connectivity. However, the diversity of channel conditions—from sparse to dense and static to fast-varying—fundamentally challenges traditional single and fixed estimation algorithms. To address this issue, this paper proposes a Physics-Prioritized Mixture of Experts (PP-MoE) scheme, leveraging the MoE paradigm’s ability to allocate resources to specialized experts tailored for distinct physical environments. The proposed scheme features an innovative heterogeneous expert library, where the architecture of each expert is customized with embedded physical priors to match its specific propagation environment. To enable intelligent scheduling, we design a hybrid decision gating network that collaboratively leverages physical formula computation and data-driven deep learning to achieve accurate channel environment identification and expert routing. Furthermore, to overcome the expert collapse problem, we propose a three-stage training strategy—pretraining, freezing, and fine-tuning to ensure training stability specialization. Extensive simulations demonstrate that PP-MoE significantly outperforms traditional and deep learning baselines. Notably, in the low-SNR region (0–15 dB), it achieves an NMSE nearly an order of magnitude lower than LMMSE. Additionally, PP-MoE maintains high efficiency with only 0.0256 GFLOPs. This work provides an effective paradigm for designing adaptive and physically reliable wireless physical layers.

Wireless federated learning (FL) facilitates collaborative training of artificial intelligence (AI) models to support ubiquitous intelligent applications at the wireless edge. However, the inherent constraints of limited wireless resources inevitably lead to unreliable communication, which poses a significant challenge to wireless FL. To overcome this challenge, we propose Sign-Prioritized FL (SP-FL), a novel framework that improves wireless FL by prioritizing the transmission of important gradient information through uneven resource allocation. Specifically, recognizing the importance of descent direction in model updating, we transmit gradient signs in individual packets and allow their reuse for gradient descent if the remaining gradient modulus cannot be correctly recovered. To further improve the reliability of transmission of important information, we formulate a hierarchical resource allocation problem based on the importance disparity at both the packet and device levels, optimizing bandwidth allocation across multiple devices and power allocation between sign and modulus packets. To make the problem tractable, the one-step convergence behavior of SP-FL, which characterizes data importance at both levels in an explicit form, is analyzed. We then propose an alternating optimization algorithm to solve this problem using the Newton-Raphson method and successive convex approximation (SCA). Simulation results confirm the superiority of SP-FL, especially in resource-constrained scenarios, demonstrating up to 9.96% higher testing accuracy on the CIFAR-10 dataset compared to existing methods.

The integration of movable antenna (MA) technique into unmanned aerial vehicle (UAV) communications offers a promising solution to reliable and energy-efficient non-terrestrial networking for low-altitude economy. To characterize multi-MA-assisted UAV-to-UAV wideband fading channels, we propose a three-dimensional arbitrary-elevation two-concentric-cylinders reference model. Based on this model, we derive the space-time-frequency correlation function (STF-CF) in closed form. From the STF-CF, we also obtain the space-Doppler power spectral density (SD-PSD) and the power space-delay spectrum (PSDS). The excellent agreement between the theoretical PSDS and some previously reported measurement data demonstrates the utility of the reference model. We then establish corresponding simulation models, which produce consistent results with the derived expressions. By leveraging the closed-form correlation function, the gradient of the log-determinant of spatial correlation matrix with respect to the MA positions can be conveniently obtained, which may serve as a method to maximize the ergodic capacity of the multi-MA assisted wideband UAV-to-UAV channels.

We propose an innovative physical layer authentication method, leveraging deep learning to robustly safeguard millimeter wave communications against pilot contamination and clone attacks. Unlike traditional upper-layer authentication mechanisms, our method capitalizes on the spatial-temporal characteristics of millimeter wave channels to extract unique fingerprints, thus establishing a lightweight channel-based authentication technique. Existing methods largely overlook pilot contamination attacks, which may severely degrade the performance of physical layer authentication. Furthermore, traditional threshold-based methods struggle to differentiate between multiple nodes, while supervised learning-based methods are practically constrained due to the unavailability of attackers’ instantaneous channel state information. Moreover, traditional real-valued deep neural networks are inefficient in utilizing the phase information of complex-valued channels, rendering them inadequate for designing practical physical layer authentication schemes. To address these challenges, we propose an autoencoder, empowered by an alternating direction method of multipliers, which can detect and mitigate pilot contamination attacks by exploiting the inherent sparsity of channels. Subsequently, we design a weighted loss function to optimize the proposed classifiable autoencoder to strike an effective balance between detecting clone attacks and authenticating multiple nodes. Finally, to further enhance feature extraction from complex-valued channels, we customize a complex-valued classifiable autoencoder incorporating an innovative complex-valued long short-term memory module. Our simulation results unveil that the proposed method significantly outperforms existing approaches in maintaining high authentication accuracy even under pilot contamination, achieving a desirable trade-off between false alarm and detection rates. Additionally, our proposed complex-valued neural networks further enhance the accuracy of clone attack detection and multiple legitimate nodes authentication.

In response to the escalating communication demand, transceivers are transforming from a data-oriented to an artificial intelligence (AI)-driven semantic-aware paradigm. However, current semantic-aware transceivers fail to simultaneously adapt to unseen data without labels and guarantee low data processing latency because strong generalization ability requires large-scale models with robust semantic understanding, while low latency leads to small model size and simple structure. To this end, we propose a feature-foundation model evolution framework deployed at cloud, edge, and users, where models with different scales can cooperate to address these issues. Specifically, the transmitter at edge sends images to the users by performing real-time semantic feature extraction and data encoding, and the small feature model is evolved with the aid of a large foundation model at cloud when unseen data occurs. To simultaneously update the feature model and avoid loss of previously acquired semantic understanding, we design a feature-foundation model evolution scheme where outputs of both foundation and feature models are leveraged. Additionally, to tackle coupled communication-computation resources for evolution, we formulate the resource scheduling problem and design algorithms to minimize the evolution latency. We conduct rigorously-designed simulation to validate the effectiveness of our framework.

This paper investigates intelligent predictive beamforming design for simultaneous wireless information and power transfer-integrated sensing and communication (SWIPT-ISAC) systems for low-altitude economy wireless networks. Considering the downlink scenario where the base station aims to localize the moving targets/communication users and also transfer power to them, we formulate a weighted sum optimization problem to balance the trade-off between achievable communication rate and harvested energy, subject to sensing accuracy constraints defined by the Cramér–Rao lower bound. To address the non-convexity of the problem, we propose the Time-Spatial Fusion Network (TSFusionNet), an unsupervised deep learning (DL) framework that leverages multi-step historical channel state information for predictive beamforming design. TSFusionNet integrates convolutional and recurrent layers with a differential attention mechanism to capture spatial-temporal dependencies and mitigate non-stationary channel dynamics. We introduce a dynamic penalty-based loss function to enforce sensing constraints during training. Simulation results show that by adjusting the weight factor, the proposed method achieves a trade-off between rate and energy while meeting sensing accuracy requirements. Moreover, it significantly reduces computational complexity by up to approximately 96.8% in parameters and 81.5% in FLOPs, compared to existing DL frameworks.

Intelligent reflecting surface (IRS)-assisted integrated sensing and communications (ISAC) systems have been extensively studied to meet higher sensing requirements. For detection-oriented IRS-assisted ISAC problems, most studies have overlooked the detection interference caused by clutters and modeled simplified point-like targets. This paper investigates extended target detection in IRS-assisted ISAC systems within clutters. We present an optimal generalized likelihood ratio test detector and derive the corresponding probability of detection (PD) and probability of false alarm in closed form. Then, we jointly optimize the active and passive beamforming of the base station and IRS to maximize the PD under multi-user equipment (UE) communication rate constraints and the total transmit power constraint. We first simplify the complex objective function by proving the invariant property of a subspace projection matrix. We then present a novel alternating optimization (AO)-based algorithm to decouple the original problem into two subproblems, consequently convexified and solved using the semidefinite relaxation method. Simulations demonstrate the convergence of the proposed algorithm. The PD performance and the communication and sensing trade-off are significantly improved, compared to benchmarks.

Low Earth Orbit (LEO) satellite systems with sensing capabilities are widely regarded as promoting reliable and efficient communication services globally. This paper proposes a Multi-Satellite Collaborative Security System with Integrated Sensing and Communication (ISAC-MSC). Considering the potential benefits of LEO satellites and ISAC, we exploit sensing performance in the MSC system by jointly optimizing LEO satellite assignments, communication Beamforming (BF) vectors, and sensing BF vectors. Specifically, we design improved Continuous Particle Swarm (CP) optimization and Discrete Particle Swarm (DP) optimization algorithms to maximize the target sensing Signal-to-Noise Ratio (SNR) for LEO satellite assignments. Additionally, with respect to the BF vector optimization, we develop Power Approximation (PA) optimization algorithm, Inner Approximation (IA) optimization algorithm, and Joint Sensing and Communication BF (JSC-BF) optimization algorithm. Multiple algorithms are tightly integrated and alternately iterated. Numerical results show that: 1) the JSC-BF algorithms outperform the PA and IA algorithms in terms of sensing performance and communication secrecy rate; 2) compared to the single satellite case, the ISAC-MSC system performance approximately linear growth, and has strong extensibility; 3) with imperfect MSC synchronization case, the communication secrecy rate appears inflection point and stabilization, but the JSC-BF algorithms still have excellent performance.

In this paper, we propose leveraging rotatable antennas (RAs) to enhance near-field communication and sensing performance by exploiting a new spatial degree-of-freedom (DoF) offered by array rotation. Specifically, we investigate an RA-aided near-field integrated sensing and communication (ISAC) system, where the transmit beamformers and the array rotation angle at the base station (BS) are jointly optimized to minimize the Cramér-Rao bounds (CRBs) for angle and range estimation, while ensuring a minimum signal-to-interference-plus-noise ratio (SINR) for communication users. To gain important insights into the impact of RAs on near-field ISAC, we analyze two special cases:communication-onlyandsensing-onlytransmission. For the communication-only case, we derive therotation-awarechannel path correlation using the Fresnel integrals and analytically demonstrate that RAs provide an additional rotation gain, thereby improving communication performance. For the sensing-only case, we derive closed-formrotation-awareCRBs for near-field angle and range estimation under bothisotropicanddirectionalbeamformers. It is theoretically unveiled that array rotation improves sensing performance by concurrently reducing both CRBs. Interestingly, the optimal rotation angles that minimize these CRBs are identical. Subsequently, to address the resultant non-convex optimization problem, we propose adouble-layeralgorithm to obtain a high-quality solution, where the inner layer optimizes the transmit beamformers using semidefinite relaxation (SDR), while the outer layer determines the array rotation through a one-dimensional exhaustive search. Finally, numerical results highlight the significant performance gains of the developed RA-aided near-field ISAC system over conventional fixed-antenna ISAC systems.

Prior studies on mixed near-field and far-field communications have focused exclusively onsingle-cellscenarios, where both near-field and far-field users are served by the same base station (BS), leading tointra-cellmixed-field interference. In this paper, we consider a more general and practicalmulti-cell mixed-fieldscenario consisting of multiple cells, each serving multiple users, thus resulting in more complexinter-cellmixed-field interference. To address this new challenge, we propose leveragingrotatable antenna(RA) technology to enhance multi-cell mixed-field communication performance by exploiting the additional spatial degree-of-freedom (DoF) introduced by RA rotation to mitigate interference in an efficient way. Specifically, we study an RA-enabled multi-cell mixed-field communication system in which each BS is equipped with an RA array to serve its associated users. We formulate a network-wide sum-rate maximization problem that jointly optimizes the transmit beamforming and the rotation angles of the RA arrays, subject to per-BS power constraints and admissible array rotation limits. To gain useful insights into the role of RAs in multi-cell mixed-field communications, we first analyze a special case with a single user per cell. For this case, we obtain a closed-form expression for therotation-awareinter-cell mixed-field interference using the Fresnel integrals and analytically show that RA rotation can effectively mitigate such interference, thereby substantially improving system performance. For the general case with multiple users per cell, we develop an efficientdouble-layeralgorithm: the inner layer optimizes the transmit beamforming at each BS via semidefinite relaxation (SDR) and successive convex approximation (SCA); while the outer layer determines the rotation angles of the RA arrays using particle swarm optimization (PSO). Numerical results demonstrate that RA-enabled multi-cell systems achieve significant performance gains over conventional fixed-antenna systems, and the proposed joint design consistently outperforms various benchmark schemes.

Integrated sensing and communication (ISAC) is expected to enable the fifth-generation (5G) networks to provide ubiquitous communication and sensing. However, some high-dynamic scenarios hinder applications of conventional ISAC schemes owing to the high overhead and poor real-time performance. In this paper, we design a novel ISAC architecture and propose a large language model (LLM) based two-stage beamforming prediction scheme. Specifically, in the first stage, we develop an LLM-based approach to predict the future channel state information (CSI) according to the history echoes. Via the data preprocessing and supervised fine-tuning, the LLM can achieve effective channel prediction task with unstructured data. In the second stage, according to the predicted/estimated CSI, we formulate a beamforming optimization problem to maximize the achievable sum rate while satisfying the quality of service (QoS). Then, we propose a Primary-dual network with the unsupervised adversarial learning to handle it, facilitating the on-line beamforming. Simulation results verify that, compared with the benchmarks, our proposed beamforming prediction scheme not only enjoys a higher channel prediction accuracy but also achieves a better balance between the performance and computational complexity.

Proactive wardens can generate interference to enhance the detection performance, posing severe security threats to the legitimate transmission. Fortunately, an intelligent reflecting surface (IRS) can facilitate the covert transmission towards the proactive wardens by reconfiguring wireless channels. In this paper, we propose an IRS-assisted covert communication scheme with finite blocklength, where a proactive warden is monitoring and jamming the transmission simultaneously. Based on the warden’s optimal threshold, we can minimize the detection error probability, which is the worst case for the covert transmission. We then derive two constraints on the average covertness utilizing the Gaussian-Chebyshev integral and upper bound scaling, respectively. Subsequently, we calculate the average decoding error probabilities for both the optimal and random IRS phases. To improve the effective throughput while ensuring the covertness, the transmit power, transmission rate, and blocklength are jointly optimized. After deriving the optimal transmit power and transmission rate, the blocklength can be obtained in a closed form or via the numerical searching based on its serving range. Simulation results are presented to demonstrate the superiority of the proposed scheme, and the tradeoff between the covertness and the effective throughput is revealed.

Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based generative models with the gradient boosting algorithm, a multi-step supervised learning algorithm, to solve supervised learning tasks. However, existing generative model algorithms are often limited by the stochastic nature of the models and the long inference time, impacting prediction performances. Therefore, we propose a Supervised Score-based Model (SSM), which can be viewed as a gradient boosting algorithm combining score matching. We provide a theoretical analysis of learning and sampling for SSM to balance inference time and prediction accuracy. Via the ablation experiment in selected examples, we demonstrate the outstanding performances of the proposed techniques. Additionally, we compare our model with other probabilistic models, including Natural Gradient Boosting (NGboost), Classification and Regression Diffusion Models (CARD), Diffusion Boosted Trees (DBT), and non-probabilistic gradient boosting models. The experimental results show that our model outperforms existing models in both accuracy and inference time.

Sketches have proven to be useful for measuring traffic. They store measurement results in the registers of data plane switches. However, they suffer from the short of switch register resources, limiting their measurement accuracy.

This paper investigates a downlink covert communication system based on rate-splitting multiple access (RSMA), assisted by a reconfigurable intelligent surface (RIS) and a jammer. This scheme treats every user in the system as requiring covert transmission and splits each user's message stream into common and private parts to meet the covert communication demands in multi-user scenarios. We derive a closed-form approximate expression for the average minimum detection error probability (AMDEP). Through extensive simulations, the correctness of the analysis and the covertness of the communication system are validated.

Mobile edge computing (MEC) is a promising technique to improve the computational capacity of smart devices (SDs) in Internet of Things (IoT). However, the performance of MEC is restricted due to its fixed location and limited service scope. Hence, we investigate an unmanned aerial vehicle (UAV)assisted MEC system, where multiple UAVs are dispatched and each UAV can simultaneously provide computing service for multiple SDs. To improve the performance of system, we formulated a UAV-based trajectory control and resource allocation multi-objective optimization problem (TCRAMOP) to simultaneously maximize the offloading number of UAVs and minimize total offloading delay and total energy consumption of UAVs by optimizing the flight paths of UAVs as well as the computing resource allocated to served SDs. Then, consider that the solution of TCRAMOP requires continuous decision-making and the system is dynamic, we propose an enhanced deep reinforcement learning (DRL) algorithm, namely, distributed proximal policy optimization with imitation learning (DPPOIL). This algorithm incorporates the generative adversarial imitation learning technique to improve the policy performance. Simulation results demonstrate the effectiveness of our proposed DPPOIL and prove that the learned strategy of DPPOIL is better compared with other baseline methods.

Integrated Sensing and Communication (ISAC) is driving the evolution of edge intelligence. In ISAC-enabled wireless edge networks, federated learning (FL) is crucial for realizing edge intelligence by supporting the networks with privacy protection, efficient data management, and dynamic adaptability. Specifically, FL allows distributed computing nodes (e.g., sensor devices) to first train local models by using data collected or sensed via ISAC and subsequently send them to one or multiple aggregation nodes for global model collaboration. However, traditional FL frameworks face significant challenges in the ISAC scenarios. For example, the privacy sensitivity of heterogeneous sensor data and the lack of transparency in model parameter exchange make it difficult to ensure the credibility of local and global models. Sharding distributed ledger technology (DLT), which divides the ledger into smaller and manageable shards, offers a potential solution to address these challenges by utilizing multi-node trust capabilities to facilitate distributed consensus during FL training. In this paper, we propose a trusted FL framework that incorporates sharding DLT within ISAC-enabled wireless edge networks to enhance both model training and consensus performance. Specifically, we develop a theoretical model to examine the interactions between model training performance and network capacities of sensing nodes (e.g., storage, computing, and communication capabilities) based on ISAC’s real-time channel state information. Based on this theoretical model, we design a trusted clustering scheme for aggregating local models. Numerical results demonstrate that in ISAC-enabled wireless edge networks, our proposed scheme significantly increases network throughput for model transmission while ensuring optimal model learning performance compared to some classical baselines.

Integrated sensing and communication (ISAC) technology is crucial for next-generation underwater networks. However, covering multiple users and targets and balancing sensing and communication performance in complex under-water acoustic (UWA) environments remains challenging. This paper proposes an interleaved orthogonal frequency division multiplexing-based MIMO UWA-ISAC system, which employs a horizontal array to simultaneously transmit adaptive waveforms for downlink multi-user communication and omnidirectional target sensing. A multi-objective optimization framework is formulated to maximize the product of communication rate and range (PRR) while ensuring sensing performance and peak-to-average power ratio (PAPR) constraints. To solve this mixed-integer nonconvex problem, a two-dimensional grouped random search algorithm is developed, efficiently exploring subcarrier interleaved patterns and resource allocation schemes. Numerical simulations under real-world UWA channels demonstrate the designed system’s superiority and effectiveness: our algorithm achieves 90% faster convergence than conventional exhaustive search with only a marginal 0.5 kbps•km PRR degradation. Furthermore, the proposed resource allocation scheme maintains robustness beyond the baseline allocation schemes under stringent PRR and PAPR constraints.

Semantic communication (SemCom) has recently emerged as a promising paradigm for next-generation wireless systems. Empowered by advanced artificial intelligence (AI) technologies, SemCom has achieved significant improvements in transmission quality and efficiency. However, existing SemCom systems either rely on training over large datasets and specific channel conditions or suffer from performance degradation under channel noise when operating in a training-free manner. To address these issues, we explore the use of generative diffusion models (GDMs) as training-free SemCom systems. Specifically, we design a semantic encoding and decoding method based on the inversion and sampling process of the denoising diffusion implicit model (DDIM), which introduces a two-stage forward diffusion process, split between the transmitter and receiver to enhance robustness against channel noise. Moreover, we optimize sampling steps to compensate for the increased noise level caused by channel noise. We also conduct a brief analysis to provide insights about this design. Simulations on the Kodak dataset validate that the proposed system outperforms the existing baseline SemCom systems across various metrics.

The integration of network function virtualization (NFV) with mobile edge computing (MEC) fosters a more agile service provisioning in a network operational cost-efficient manner. However, some challenges exist in adapting to the unpredictable network stochastics and resource restrictiveness, when placing virtualized network functions (VNFs) or service function chains (SFSs) appropriately onto MEC networks. In this work, we study the cost-efficient online SFC deployment in MEC networks, where each service is translated as an SFC flow and traverses through networks to meet service demands. First, we formulate a long-term time-averaged network operational cost minimization problem, by optimizing both SFC mapping and flow routing, to keep the system stability. Then, to deal with the non-trivial mixed-integer programming (MIP) and stochasticity properties in the SFC deployment, we use both Lp(0 <p< 1) norm-based relaxation and penalization, and learn-and-adapt techniques, to obtain an improved performance-stability tradeoff. Finally, both theoretical analyses and numerical simulations are conducted to demonstrate the proposed method’s superiority, in terms of its asymptotic optimality and reduced queue backlog.

This paper investigates the covert communication (CC) performance of a simultaneous transmission and reflection reconfigurable intelligent surface (STAR-RIS) assisted non-orthogonal multiple access (NOMA) and rate splitting (RS) systems operating over Rician fading channels. Alice applies RS and NOMA to the downlink transmission of two legitimate users aided by the STAR-RIS in the presence of two non-colluding illegal users. Specifically, closed-form expressions for detection error probability, optimal detection threshold, minimum detection error probability (MDEP) of the warden, and the covert rate of the NOMA user pair are derived. The accuracy of the derived results is verified through Monte Carlo simulations. The results demonstrate that the MDEP depends only on the power allocation factor of the covert users and is independent of the transmit power or STAR-RIS deployment distance. Furthermore, the RS-NOMA system exhibits superior CC performance compared to the conventional NOMA system.

Reliable and ultra-low-latency communication is essential for multiagent communication involving autonomous ground robots and unmanned aerial vehicles (UAVs). These mobile platforms form dynamic, multi-hop heterogeneous networks where timely delivery of critical information, such as health status or hazard detection, is vital. While average delay is commonly used, it fails to reflect the risk of rare but critical delay violations, which delay violation probability bound (DVPB) quantifies and helps predict for better planning and control. In this paper, we propose a martingale-based framework to predict the DVPB in the UAV-assisted ground robot communication networks. We specifically introduce a joint decay rate derivation method and define a stability condition to derive closed-form expressions for end-to-end DVPB in multi-hop heterogeneous networks. Simulation results demonstrate that the proposed method significantly outperforms conventional moment generating function in stochastic network calculus (MGF SNC) approaches under various network loads, hop counts, and data types. The proposed martingale-based DVPB offers accurate and reliable delay guarantees for real-world emergency communication networks.

This paper studies the joint beamforming and power allocation optimization in Low Earth Orbit (LEO) satellite networks with Rate-Splitting Multiple Access (RSMA), where dynamic channels and limited channel state information significantly degrade the performance of conventional optimization methods. Specifically, we formulate a sum-rate maximization problem under RSMA constraints. The decision variables include the transmit power allocated to the common and private streams, which are subject to total power and minimum user rate constraints. To solve this challenging problem, we propose STELLAR, a novel framework that employs a Large Language Model (LLM) as an intelligent decision-maker to directly generate feasible transmission strategies without requiring repeated model training. Specifically, STELLAR combines model-driven beamforming initialization with prompt-based evolutionary refinement and population updates, enabling rapid adaptation to varying channel conditions. Simulation results show that STELLAR outperforms baseline approaches, achieving superior spectral efficiency and converging within 30 iterations in a system with a 16-antenna LEO satellite and four ground stations.

Generative Artificial Intelligence (GenAI) models, with their powerful feature learning capabilities, have been applied in many fields. In mobile wireless communications, GenAI can dynamically optimize the network to enhance the user experience. Especially in signal detection and channel estimation tasks, due to digital signals following a certain random distribution, GenAI models can fully utilize their distribution learning characteristics. For example, diffusion models (DMs) and normalized flow models have been applied to related tasks. However, since the DM cannot guarantee that the generated results are the maximum-likelihood estimation points of the distribution during the data generation process, the successful task completion rate is reduced. Based on this, this paper proposes a Maximum-Likelihood Estimation Inference (MLEI) framework. The framework uses the loss function in the forward diffusion process of the DM to infer the maximum-likelihood estimation points in the discrete space. Then, we present a signal detection task in near-field communication scenarios with unknown noise characteristics. In experiments, numerical results demonstrate that the proposed framework has better performance than state-of-the-art signal estimators.

In this paper, we design a novel unmanned aerial vehicle (UAV) aided covert cooperative cognitive radio (CR) scheme, where a UAV as the secondary transmitter can send its own covert signal to a secondary receiver while guaranteeing the quality of service for the primary user (PU). To accomplish the covert transmission of the secondary user, the PU’s signal is applied as a friendly interference to interrupt the detection of wardens. We first calculate the minimum detection error probability and Kullback-Leibler divergence under the finite blocklength constraint. Then, the average effective throughput maximization problem under the probabilistic line-of-sight channel is constructed by jointly optimizing the UAV’s transmit power and trajectory. Finally, simulation results demonstrate that the proposed UAV-assisted cooperative CR scheme is effective for covert air-ground transmissions against multiple wardens.

Leveraging the mobility and cost-effectiveness, unmanned aerial vehicles (UAVs) are deployed in Internet of Things (IoT) systems to efficiently collect data from IoT devices (IoTDs). However, due to the broadcast nature of UAV wireless communication channels, they are highly susceptible to eavesdropping attacks, resulting in information leakage. In this paper, we investigate a dual UAV-assisted IoT data collection system under the threat of multiple eavesdroppers. Specifically, the primary UAV is responsible for collecting data from ground IoT devices, while the jamming UAV generates jamming signals to interfere with eavesdroppers. We aim to minimize the age of information (AoI) of the IoTDs and the energy consumption of dual UAVs by jointly optimizing UAV trajectories and IoTD scheduling. Given the non-convex mixed-integer nature of this problem, traditional optimization methods struggle to deal with this without precise prior knowledge. Therefore, we propose a denoising diffusion probabilistic model-based twin delayed deep deterministic policy gradient (DDPM-TD3) algorithm. Specifically, we leverage the data modeling capability of the DDPM by integrating it with the actor network of TD3 to generate more rational actions. Simulation results indicate that DDPM-TD3 algorithm can effectively enhance the AoI performance and energy efficiency compared to several existing deep reinforcement learning benchmarks.

In this paper, we explore an unmanned aerial vehicle (UAV)-assisted Internet-of-Things (IoT) data collection system, where multiple UAVs are deployed and each UAV can simultaneously collect data from multiple IoT devices. Specifically, we formulate a UAV-enabled data collection multi-objective optimization problem (UDCMOP) to simultaneously maximize the collected data of UAVs and minimize the total energy consumption of UAVs that contains the moving and hovering energy consumption by optimizing the flight trajectories of UAVs. Given the dynamic nature of the system and the need for coordination among multiple UAVs, we propose an enhanced multi-agent deep reinforcement learning (MADRL) algorithm, namely, multi-agent proximal policy optimization with curiositydriven exploration (MAPPOC). This algorithm incorporates a curiosity-driven exploration mechanism to improve exploration capabilities. Simulation results demonstrate the effectiveness of the proposed MAPPOC and prove that the learned strategy of MAPPOC is better compared with other baseline methods.

Emerging services such as augmented reality (AR) and virtual reality (VR) have increased the volume of data transmitted in wireless communication systems, revealing the limitations of traditional Shannon theory. To address these limitations, semantic communication has been proposed as a solution that prioritizes the meaning of messages over the exact transmission of bits. This paper explores semantic communication for text data transmission in end-to-end (E2E) systems through a novel approach called KG-LLM semantic communication, which integrates knowledge graph (KG) extraction and large language model (LLM) coding. In this method, the transmitter first utilizes a KG to extract key entities and relationships from sentences. The extracted information is then encoded using an LLM to obtain the semantic meaning. On the receiver side, messages are decoded using another LLM, while a bidirectional encoder representations from transformers (i.e., BERT) model further refines the reconstructed sentences for improved semantic similarity. The KG-LLM semantic communication method reduces the transmitted text data volume by $30 \%$ through KG-based compression and achieves $84 \%$ semantic similarity between the original and received messages. This demonstrates the KG-LLM methods efficiency and robustness in semantic communication systems, outperforming the deep learning-based semantic communication model (DeepSC), which achieves only $63 \%$.

Integrated sensing and communication (ISAC) is emerging as a crucial technology for 6G networks, with channel state information (CSI) based ISAC playing a vital role. These systems utilize various AI models to process and analyze the CSI extracted from wireless communication signals, thereby enabling monitoring of physical spaces and human activities. However, due to the costs and privacy issues, collecting sufficient training CSI data is challenging. In response, this paper proposes a data augmentation system based on the diffusion model. Specifically, we first use the limited samples collected from real-world ISAC scenarios to train a conditional diffusion model, which then generates new samples to enhance sample quantity. Subsequently, we train another diffusion model with noise-free data to reduce noise in these generated samples, thereby further enhancing the sample quality. The evaluation based on the real-world CSI data validates that our approach can effectively enhance the data from both quantity and quality perspectives, thereby supporting the model training in ISAC networks.

The combination of reconfigurable intelligent surface (RIS) and integrated sensing and communication (ISAC) can improve the resource utilization in non-line-of-sight scenarios. However, the private information in this situation raises security concerns when the transmission behavior is detected by wardens. Against this background, we investigate a covert transmission problem in an RIS assisted ISAC system. Specifically, we obtain a tractable form of covertness constraint in terms of minimum detection error probability via the optimal detection threshold, paving the way for optimization process. Then, the sum covert transmission rate is maximized by jointly optimizing the beamforming of confidential signal and jamming signal as well as the RIS’s phase shift. To solve the above non-convex problem, we propose a joint covert beamforming and the phase shift of RIS optimization-based twins-deep deterministic policy gradient (CBP-TD3) algorithm. Finally, simulation results demonstrate the effectiveness of the proposed CBP-TD3 algorithm in the covertness.

Federated Learning has garnered significant attention in practical applications due to its privacy-preserving properties but faces serious threats from backdoor attacks. Current defenses primarily rely on server-side anomaly detection and robust aggregation, but lack systematic strategies for proactively erasing backdoors from the perspective of attackers. To bridge this gap, we propose an efficient and stealthy federated backdoor removal framework. Specifically, our method incorporates a two-stage training approach: reinforced negative learning and positive memory recovery. In addition, we intro-duce a hybrid regularization strategy that combines dynamic L1 regularization with Elastic Weight Consolidation, together with a synchronized differential amplification mechanism for both weights and buffers and a global norm clipping strategy. These components collectively effectively erase backdoor effects, maintain main-task accuracy, and significantly reduce detection risk on the server side. Experimental evaluations demonstrate that, compared to existing backdoor unlearning methods, our approach decreases the success rate of the backdoor attack by up to 11% without compromising the primary precision. Furthermore, our method substantially improves the stealthiness of the update, reducing the L2 norm fluctuations to less than 33% of the baseline levels.

Large Language Models (LLMs) in intelligent automotive systems offer significant benefits, such as enhancing natural language understanding, improving user interaction, and enabling more intelligent decision-making. However, this integration also faces important challenges, including data heterogeneity, limited computational resources, and the critical need to safeguard user privacy. Federated Learning (FL) offers a promising solution by enabling decentralized training across distributed data sources without compromising privacy. This paper proposes a novel FL framework for in-vehicle systems, addressing key challenges such as data heterogeneity and limited computational resources. Our method introduces a robust aggregation algorithm based on the L2 norm between LLM increments, effectively mitigating data inconsistencies and enhancing model generalization. Moreover, by integrating Low-Rank Adaptation (LoRA) within parameter-efficient fine-tuning, the framework reduces computational and communication overhead while preserving privacy. Comprehensive experiments validate that the proposed method outperforms state-of-the-art FL methods, achieving a Vicuna score of 8.17, a harmless answer rate of 68.65% (Advbenchmark), and an MTBenchmark average score of 3.74. These results highlight the potential of the proposed FL-based LLM with the LoRA framework in revolutionizing intelligent automotive systems through enhanced adaptability and privacy preservation.

LoRa-based backscatter communication technology is promising in enabling ubiquitous connectivity for the Internet of Things (IoT) over large distances with extremely low power consumption. In this paper, we design and implement CPLoRa, a high-throughput parallel LoRa backscatter communication system compatible with commodity LoRa receivers. The core idea of CPLoRa is to enable multiple backscatter tags to communicate with remote LoRa receivers simultaneously by generating standard LoRa packets from a common single-tone RF emitter, which can be extracted from ambient LoRa transmitters or generated from dedicated mobile devices. CPLoRa employs a modified low-power direct digital synthesizer (DDS) scheme for precise frequency synthesis, ensuring compatibility with commodity LoRa receivers and enhancing data rates for long-range backscatter transmissions. Each tag is assigned a unique frequency offset in the synthesizer, allowing parallel transmissions and creating orthogonal, independent LoRa channels. Moreover, we design a harmonic-canceling switch network at the RF front end to reduce mutual interference among different tags. Finally, we implement the CPLoRa tag prototype using low-cost circuit components and rigorously tested in outdoor and indoor environments, demonstrating that CPLoRa supports long-range transmissions of up to 1000 meters while achieving a throughput of 9.6 kbps with 10 parallel tags compatible with commodity LoRa receivers.

Flying ad hoc networks (FANETs) composed of small unmanned aerial vehicles (UAVs) are flexible, inexpensive, and fast to deploy, which have been used in an increasing number of mission scenarios. However, unstable link quality and frequently changing network topology pose significant challenges for adopting existing routing protocols in mobile ad hoc networks (MANETs). In this paper, we propose a time-slotted on-demand predictive (TSDP) routing protocol designed specifically for UAV networks. The TSDP protocol introduces a novel approach to route selection by incorporating multiple criteria, including delivery ratio, adjacent degree, and mobility prediction factor, to ensure reliable and efficient data transmission. By addressing high latency in route discovery and excessive broadcast overhead, TSDP employs a time-slotted communication mechanism that reduces packet drop rates and enhances route stability. Simulation results demonstrate that TSDP consistently outperforms ad hoc on-demand distance vector (AODV) and dynamic source routing (DSR) protocols in terms of throughput, packet delivery ratio, end-to-end delay, and overhead, particularly in highly dynamic network environments.

Multi-dimensional spectrum prediction is essential for spectrum sharing and dynamic spectrum access (DSA), tack-ling spectrum scarcity and improving wireless communication. Traditional methods often use machine learning (ML), which requires manual feature extraction, or deep learning (DL), which demands high computational resources. This paper proposes a lightweight multi-dimensional spectrum prediction model using an adaptive broad learning network (ABLN). The model employs a sliding window to preprocess data and establishes input layers using randomly generated feature and enhancement nodes. The weights of broad learning are determined by solving the pseudo-inverse, and the structure is incrementally extended without retraining, reducing computational complexity. An adaptive node increment module optimizes hyperparameters efficiently. Experimental results demonstrate that ABLN reduces computational overhead while maintaining robust prediction performance across various scenarios.

With the rapid advancement of artificial intelligence (AI), generative AI (GenAI) has emerged as a transformative tool, enabling customized and personalized AI-generated content (AIGC) services. However, GenAI models with billions of parameters require substantial memory capacity and computational power for deployment and execution, presenting significant challenges to resource-limited edge networks. In this paper, we address the joint model caching and resource allocation problem in GenAI-enabled wireless edge networks. Our objective is to balance the trade-off between delivering high-quality AIGC and minimizing the delay in AI GC service provisioning. To tackle this problem, we employ a deep deterministic policy gradient (DDPG)-based reinforcement learning approach, capable of efficiently determining optimal model caching and resource allocation decisions for AIGC services in response to user mobility and time-varying channel conditions. Numerical results demonstrate that DDPG achieves a higher model hit ratio and provides superior-quality, lower-latency AIGC services compared to other benchmark solutions.

This paper investigates an unmanned aerial vehicle (UAV)-assisted semantic communication network. The energy-limited ground users (GUs) provide semantic services to periodically generated raw data and a UAV relays the extracted semantic information to a base station (BS). Semantic extraction enhances data responsiveness and reduces the age-of-information (AoI) by transmitting only the most essential information. However, more complex semantic extraction increases energy consumption, making it easier for the GUs to deplete their energy. Therefore, we introduce a novel energy-efficient AoI (EAoI) metric to capture both information freshness and energy consumption of the GUs. We formulate a time-averaged EAoI minimization problem by jointly optimizing the GUs' scheduling, pre-extraction strategy, semantic control, computing resource allocation, and the UAV's trajectory. We further propose a semantic-aware joint pre-extraction and trajectory planning (Sem-JPT) algorithm to decompose the complex optimization problem into three subproblems, which are solved by a series of approximation methods. Simulation results demonstrate that semantic communication can reduce the overall EAoI by more than 18% compared with conventional bit-based communication. Moreover, the proposed Sem-JPT algorithm can maintain information freshness and prolong the GUs' lifetimes, outperforming existing baselines.

Specific emitter identification (SEI) is crucial in the Internet of Everything (IoE). Over the past decade, deep learning (DL) and broad learning (BL)-enabled SEI technologies have emerged. Recently, many researchers have begun exploring semi-supervised learning techniques to address the semi-supervised SEI (SS-SEI) problem with limited labeled RF signals. However, existing SS-SEI solutions often prioritize identification performance, leading to high computational overheads and lacking iterability. To overcome these challenges, this paper proposes a novel SS-SEI solution based on a learnable broad learning network (LBL). Initially, a pretrained DL-based SEI model is downloaded to the edge device. Meanwhile, an updatable BL-based SEI method is deployed locally on the edge device to identify unlabelled signals. When the LBL solution is operational, edge devices capture real-time unlabelled RF signals. The pretrained DL-based SEI method and the locally BL-based SEI method jointly identify these RF signals. The identification results and the new real-time RF signals are then used to update the weights of the BL-based SEI method at the edge devices. The LBL SS-SEI solution is validated using an open-source, large-scale, real-world automatic dependent surveillance-broadcast (ADS-B) dataset. Experimental results demonstrate that the proposed LBL solution offers significant advantages regarding SS-SEI performance.

Abstract With the growing demand for seamless connectivity and intelligent communication, the integration of artificial intelligence (AI) and sixth-generation (6G) communication networks has emerged as a transformative paradigm. By embedding AI capabilities across various network layers, this integration enables optimized resource allocation, improved efficiency, and enhanced system robust performance. This paper presents a comprehensive overview of AI and communication for 6G networks, with a focus on their foundational principles, inherent challenges, and future research opportunities. We first review the integration of AI and communications in the context of 6G, exploring the driving factors behind incorporating AI into wireless communications, as well as the vision for the convergence of AI and 6G. The discourse then transitions to a detailed exposition of the envisioned integration of AI within 6G networks, divided into three progressive stages. The first stage, AI for network, focuses on employing AI to augment network performance, optimize efficiency, and enhance user service experiences. The second stage, network for AI, highlights the role of the network in facilitating and buttressing AI operations and presents key enabling technologies. We compare wireless network large models with conventional large language models (LLMs), and identify key design principles and components for building wireless network architectures. In the final stage, AI as a service, it is anticipated that future 6G networks will innately provide AI functions as services, supporting application scenarios like immersive communication and intelligent industrial robots. Specifically, we define the quality of AI service, which refers to a framework for measuring AI services within the network. We further summarize the standardization process of AI for wireless networks, highlighting key milestones and ongoing efforts. In addition, we analyze the critical challenges faced by the integration of AI and communications in 6G. Finally, we outline promising future research opportunities that are expected to drive the development and refinement of AI and 6G communications.

The rapid expansion of Internet of Things (IoT) technologies has introduced significant cybersecurity challenges, particularly at the network edge where IoT devices operate. Traditional security policies designed for static environments fall short of addressing the dynamic, heterogeneous, and resource-constrained nature of IoT ecosystems. Existing dynamic security policy models lack versatility and fail to fully integrate comprehensive risk assessments, regulatory compliance, and AI/ML (artificial intelligence/machine learning)-driven adaptability. We develop a novel adaptive edge security framework that dynamically generates and adjusts security policies for IoT edge devices. Our framework integrates a dynamic security policy generator, a conflict detection and resolution in policy generator, a bias-aware risk assessment system , a regulatory compliance analysis system, and an AI-driven adaptability integration system. This approach produces tailored security policies that adapt to changes in the threat landscape, regulatory requirements, and device statuses. Our study identifies critical security challenges in diverse IoT environments and demonstrates the effectiveness of our framework through simulations and real-world scenarios. We found that our framework significantly enhances the adaptability and resilience of IoT security policies. Our results demonstrate the potential of AI/ML integration in creating responsive and robust security measures for IoT ecosystems. The implications of our findings suggest that dynamic and adaptive security frameworks are essential for protecting IoT devices against evolving cyber threats, ensuring compliance with regulatory standards, and maintaining the integrity and availability of IoT services across various applications.

Cell-free networks have emerged as a new paradigm for beyond-5G networks, offering uniform coverage and improved control over interference. However, scalability poses a challenge in full cell-free networks, where all access points (APs) serve all users. This challenge is addressed by user-centric clustering, where each user is served by a subset of APs, reducing complexity while maintaining coverage. In this paper, we provide an analysis of the relation between the user-centric clustering and pilot assignment problems in cell-free networks, and introduce a formulation which decouples both problems enabling each to be solved independently. We present a general problem formulation for the user-centric clustering problem, allowing the use of diverse per-user and network-wide performance metrics. Specifically, we focus on one instance of this framework, utilizing per-user spectral efficiency and network-wide sum spectral efficiency (SE) as metrics. Additionally, we formulate the pilot assignment problem to minimize overall channel estimation error while considering the user-centric clusters in evaluating the desirability of pilot assignments, which leads to better performing solutions. Both problems are classified as binary nonlinear programs that are at least NP-hard. To solve these optimization problems, our proposed methodology employs sample average approximation coupled with surrogate optimization for the user-centric clustering problem and utilizes the genetic algorithm for the pilot assignment problem. Numerical experiments demonstrate that the optimized solutions surpass baseline solutions, leading to significant improvements in spectral efficiency.

We consider decentralized federated learning (DFL) in unmanned aerial vehicle (UAV) networks where UAVs collaboratively train their machine learning (ML) models in a serverless peer-to-peer manner without sharing local data. We focus on three challenges affecting the performance and feasibility of UAV-aided DFL: i) communication inefficiency, ii) dynamics, heterogeneity and energy constraints of UAV networks, and iii) high synchronization overheads. To address these challenges, we propose an asynchronous DFL (A-DFL) model for UAV networks and design a novel distributed, adaptive and energy-aware model compression method based on the gradient sparsification. In this method, UAVs communicate asynchronously and apply the time-varying and non-identical compression parameters to adjust to a dynamic, heterogeneous environment. This reduces synchronization overheads and improves the communication efficiency given the strict battery constraints of UAVs. We show that our method can be formulated as a Markov potential game where the UAVs act as the players which decide on their compression parameters and the number of training data samples used for model updates. We prove that our game admits a dominant pure-strategy Nash equilibrium (NE) that maximizes its potential function and develop a new sparsified A-DFL algorithm enabling every UAV to reach its dominant strategy independently, in polynomial time. We then prove that the proposed algorithm converges to the Pareto-optimal NE representing the most efficient solution of our game. Using extensive simulations, we verify that our algorithm outperforms the state-of-the-art methods in terms of the key evaluation metrics of DFL.

The integration of simultaneous wireless information and power transfer (SWIPT) technology in 6G Internet of Things (IoT) networks faces significant challenges in remote areas and disaster scenarios where ground infrastructure is unavailable. This paper proposes a novel unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) system enhanced by directional antennas to provide both computational resources and energy support for ground IoT terminals. However, such systems require multiple trade-off policies to balance UAV energy consumption, terminal battery levels, and computational resource allocation under various constraints, including limited UAV battery capacity, non-linear energy harvesting characteristics, and dynamic task arrivals. To address these challenges comprehensively, we formulate a bi-objective optimization problem that simultaneously considers system energy efficiency and terminal battery sustainability. We then reformulate this non-convex problem with a hybrid solution space as a Markov decision process (MDP) and propose an improved soft actor-critic (SAC) algorithm with an action simplification mechanism to enhance its convergence and generalization capabilities. Simulation results have demonstrated that our proposed approach outperforms various baselines in different scenarios, achieving efficient energy management while maintaining high computational performance. Furthermore, our method shows strong generalization ability across different scenarios, particularly in complex environments, validating the effectiveness of our designed boundary penalty and charging reward mechanisms.

This paper addresses the challenge of optimizing multi-hop routing in IoT-based digital twin systems, referred to as the MOUNTAIN problem. Multi-hop routing is inherently complex due to the need to balance energy consumption and communication reliability across multiple nodes, especially in dynamic and large-scale IoT networks. In MOUNTAIN, multiple IoT devices in the physical network (PN) frequently transmit data to the digital network twin (DNT), managed by a central server. Given the limited energy resources of IoT devices, our approach considers both energy efficiency and communication reliability. We formulate the MOUNTAIN problem as an optimization task aimed at reducing overall energy consumption while maintaining robust data transmission. Moreover, we address the problem with both single-task optimization and multi-task optimization and propose two corresponding evolution-based metaheuristics that utilize well-designed solution representations and genetic operators to obtain near-optimal solutions to the problem. Among them, the proposed Single-task Evolutionary Algorithm (STEA) solves each problem instance independently, while the proposed Multi-task Evolutionary Algorithm (MTEA) solves multiple instances at the same time to take advantage of exchanging useful solution information during parallel solution searches. Extensive experiments on synthetic datasets demonstrate that our proposed algorithms significantly outperform existing methods, reducing energy consumption and improving network stability. This research contributes to the development of sustainable and efficient IoT infrastructures, which are essential for the operational demands of digital twin applications.

Anomaly detection in human activity recognition (HAR) is a critical subfield that leverages data from the Internet of Things (IoT) to monitor human activities and detect errors or abnormal events. Conventional rule-based approaches often fail to capture the intricate relationships between sensor values, while machine-learning-based methods tend to lack the ability to provide explainability and actionable context for the detected anomalies. In this article, we introduce a novel correlation-based anomaly detection framework designed to improve the security and reliability of IoT-enabled HAR systems. Our proposed scheme utilizes a context-aware deep learning architecture to predict sensor values by leveraging the interdependencies between coexisting sensors in the deployment environment. Experimental results demonstrate that our model achieves a best anomaly prediction accuracy of 99.76% on individual sensors and outperforms other baseline models, consistently maintaining high F1 scores with a minimum of 0.866 on various sensors, even when the training dataset is reduced. Furthermore, we propose an AI-generated content (AIGC)-based visualization method for reporting anomalies, offering clear insights into the context and severity of detected anomalies and their potential system impact.

Malicious jamming attacks pose a significant threat to the integrity and performance of Internet of Things (IoT) networks. However, many jamming patterns are rare or infrequent, which makes them difficult to counter effectively. This article addresses the critical issue of anti-jamming (AJ) under few-shot sample conditions in IoT networks. Source separation is a key component of AJ communication. Although deep learning-based source separation has demonstrated significant advantages, it typically requires a large amount of labeled data, which can be impractical in certain environments. To overcome this challenge, we propose two novel schemes that leverage multitask learning (MTL) and meta-learning (ML) to enhance the model’s signal separation capabilities within the constraints of limited sample scenarios. MTL enhances robustness by leveraging shared representations across tasks, while ML allows for rapid adaptation to novel jamming signals with minimal samples. Specifically, we employ a modified separation model, SepFormer, as our baseline and integrate MTL and ML schemes to enable the separation of unknown or few-shot jamming signals. Additionally, we have constructed two datasets encompassing both simulated and real-world environmental data to test and evaluate the performance of the proposed methods. Simulation results demonstrate the superior AJ performance of our schemes, particularly when compared with a direct application of the separation model with few-shot samples. Furthermore, our evaluation of performance across various jamming scenarios and interference-to-signal ratios (ISRs) further confirms the effectiveness of our proposed scheme.

The rapid expansion of data from diverse sources has made anomaly detection (AD) increasingly essential for identifying unexpected observations that may signal system failures, security breaches, or fraud. As datasets become more complex and high-dimensional, traditional detection methods struggle to effectively capture intricate patterns. Advances in deep learning have made AD methods more powerful and adaptable, improving their ability to handle high-dimensional and unstructured data. This survey provides a comprehensive review of over 190 recent studies, focusing on deep learning-based AD techniques. We categorize and analyze these methods into reconstruction-based and prediction-based approaches, highlighting their effectiveness in modeling complex data distributions. Additionally, we explore the integration of traditional and deep learning methods, highlighting how hybrid approaches combine the interpretability of traditional techniques with the flexibility of deep learning to enhance detection accuracy and model transparency. Finally, we identify open issues and propose future research directions to advance the field of AD. This review bridges gaps in existing literature and serves as a valuable resource for researchers and practitioners seeking to enhance AD techniques using deep learning.

Autonomous aerial vehicles (AAVs) can be utilized as relay platforms to assist maritime wireless communications. However, complex channels and multipath effects at sea can adversely affect the quality of AAV transmitted signals. Collaborative beamforming (CB) can enhance the signal strength and range to assist the AAV relay for remote maritime communications. However, due to the open nature of AAV channels, security issue requires special consideration. This article proposes a dual AAV cluster-assisted system via CB to achieve physical-layer security in maritime wireless communications. Specifically, one AAV cluster forms a maritime AAV-enabled virtual antenna array (MUVAA) relay to forward data signals to the remote legitimate vessel, and the other AAV cluster forms an MUVAA jammer to send jamming signals to the remote eavesdropper. In this system, we formulate a secure and energy-efficient maritime communication multiobjective optimization problem (SEMCMOP) to maximize the signal-to-interference-plus-noise ratio (SINR) of the legitimate vessel, minimize the SINR of the eavesdropping vessel and minimize the total flight energy consumption of AAVs. Since the SEMCMOP is an NP-hard and large-scale optimization problem, we propose an improved swarm intelligence optimization algorithm with chaotic solution initialization and hybrid solution update strategies to solve the problem. Simulation results indicate that the proposed algorithm outperforms other comparison algorithms, and it can achieve more efficient signal transmission by using the CB-based method.

Digital Twin (DT) technology is transforming biological processes by enabling real-time predictive modeling and optimization. However, implementing DTs at the micro- and nano-scale presents significant challenges in data extraction, transmission, and computation due to the complexity of biological environments. To address these challenges, this work proposes a multi-model Physics-Informed Neural Network (PINN) framework, enhanced by the Internet of Bio-Nano Things (IoBNT), to improve real-time bioprocess monitoring and prediction. The proposed framework integrates IoBNT for efficient biological data acquisition and transmission with advanced deep neural networks (DNNs), including Fully Connected Neural Networks (FCNN), Residual Block Neural Networks (ResBlock NN), and Recurrent Neural Networks (RNN), to enhance predictive accuracy. By incorporating physics-based constraints into the learning process, the PINN architecture ensures biologically plausible and data-efficient predictions. Experimental results demonstrate the framework’s effectiveness in monitoring microbial and substrate growth using Monod equations, achieving an average mean absolute error (MAE) of 0.0275 g/L, anR2value close to 1, and a root mean squared error (RMSE) of 0.0425 g/L across four of the five proposed architectures. Additionally, the integration of IoBNT enhances data reliability, reducing transmission errors by up to 98%. These findings highlight the potential of IoBNT-powered PINN frameworks for developing high-fidelity, self-adaptive DTs in digital biological and healthcare applications.

Multibeam low-Earth orbit (LEO) satellite communication is a promising solution for providing high-data rate and wide area coverage. Therefore, satellite communication is introduced into Internet of Things (IoT) networks to support large-scale connectivity. In the satellite communication system, multibeam management and power control are challenging issues because interbeam interference severely affects system performance and power consumption influences the battery life of the satellite. Thus, traditional LEO satellite systems mainly focus on minimizing a capacity-demand gap to develop an effective power reduction algorithm. In contrast to this approach, in this article, we present a theoretical analysis of the optimal conditions for minimizing the transmit power of the satellite while satisfying the traffic demands of users in multibeam LEO satellite-assisted IoT networks. Based on this analysis, we propose algorithms for user-beam association, beam pattern selection, timeslot scheduling, and power allocation to minimize the transmit power while satisfying the traffic demands. In addition, we provide low-complexity algorithms for power minimization to reduce the computational complexity. Simulation results demonstrate that the proposed methods outperform the conventional schemes in terms of power consumption, capacity-demand gap, and computational complexity.

The integration of Tiny Machine Learning (TinyML) with Human Behavior Analysis (HBA) represents a significant advancement in the field of Artificial Intelligence (AI), enabling real-time, efficient, and privacy-preserving analysis on resource-constrained devices. This paper provides the first comprehensive survey exploring this integration, presenting a detailed overview of TinyML, including its definitions, key concepts and advantages. The survey proposes a systematic taxonomy of TinyML applications in HBA, categorizing state-of-the-art implementations based on their use cases and specific methodologies. Furthermore, the challenges and limitations of integrating TinyML in HBA are thoroughly discussed, including technical constraints, data quality issues, and ethical considerations. Finally, future research directions and open issues are outlined, emphasizing the potential advancements and emerging trends in this field. This survey serves as a foundational resource, guiding researchers and practitioners in harnessing the capabilities of TinyML to advance HBA.

Air handwriting recognition has emerged as a promising solution for touchless human-computer interaction, particularly in the context of Internet of Things (IoT) systems and wearable devices, where traditional input modalities are often infeasible. However, despite extensive research on Latin, Arabic, and Chinese scripts, no prior work has explored real-time air-written recognition of Tifinagh characters a historically and culturally significant script used by Amazigh communities in North Africa. To address this gap, we present the first end-to-end air handwriting recognition framework for the Tifinagh alphabet, designed specifically for constrained IoT environments. At the core of our system is XTiny-FastKAN, a novel, interpretable TinyML model based on a fast variant of the Kolmogorov–Arnold Network (KAN), optimized for ultra-low-latency inference and minimal memory consumption. The system captures inertial motion signals using a consumer-grade IMU, applies a rasterization-based preprocessing pipeline, and uses temporal saliency mapping for explainable predictions. Our quantized model achieves a recognition accuracy of 96.6%, with a memory footprint of just 35 KB and an inference time of 0.04 ms, enabling real-time execution on microcontroller-class IoT hardware. This work not only fills a critical gap in the digitization of underrepresented languages but also contributes a deployable, energy-efficient, and explainable edge AI solution aligned with the growing demands of TinyML in IoT ecosystems. Our codes and dataset are available at https://github.com/Ism-ail11/XTiny-FastKAN.

In this article, we develop a dynamic weighting strategy which considers the residual energy of different devices in aerial edge computing networks, and formulate a weighted energy consumption optimization problem aimed at extending device operating duration. To solve the formulated problem, we develop a clustering algorithm using K-means++ to establish optimal user-to-unmanned-aerial-vehicle access relationships, and the optimization problem is decomposed into trajectory, transmit power, and bandwidth subproblems. Each subproblem is sequentially solved by using the successive convex approximation algorithm, and the entire optimization problem is resolved by using the block coordinate descent algorithm. Simulation results demonstrate the effectiveness of our proposed weighting strategy in managing the energy levels of users, which prolongs the operational duration of the devices.

To ensure the thriving development of low-altitude economy, countering unauthorized uncrewed aerial vehicles (UAVs) is an essential task. The existing widely deployed base stations hold great potential for joint communication and jamming (JCJ). In the light of this, this article investigates the joint design of beamforming to simultaneously support communication with legitimate users and countermeasure against unauthorized UAVs based on dual-functional multiple-input-multiple-output (MIMO) cellular systems. We first formulate a JCJ problem, relaxing it through semi-definite relaxation (SDR) to obtain a tractable semi-definite programming (SDP) problem, with SDR providing an essential step toward simplifying the complex JCJ design. Although the solution to the relaxed SDP problem cannot directly solve the original problem, it offers valuable insights for further refinement. Based on these insights, we design a novel constraint specifically tailored to the structure of the SDP problem, ensuring that the solution adheres to the rank-1 constraint of the original problem. Finally, we validate effectiveness of the proposed JCJ scheme through extensive simulations. The results confirm that the proposed JCJ scheme can operate effectively when the total number of legitimate users and unauthorized UAVs exceeds the number of antennas. Simulation codes are provided to reproduce the results in this article:https://github.com/LiZhuoRan0.

An expansion of Internet of Things (IoT) has led to significant challenges in wireless data harvesting, dissemination, and energy management due to the massive volumes of data generated by IoT devices. These challenges are exacerbated by data redundancy arising from spatial and temporal correlations. To address these issues, this article proposes a novel data-driven collaborative beamforming (CB)-based communication framework for IoT networks. Specifically, the framework integrates CB with an overlap-based multihop routing protocol (OMRP) to enhance data transmission efficiency while mitigating energy consumption and addressing hot spot issues in remotely deployed IoT networks. Based on the data aggregation to a specific node by OMRP, we formulate a node selection problem for the CB stage, with the objective of optimizing uplink transmission energy consumption. Given the complexity of the problem, we introduce a softmax-based proximal policy optimization with long-short-term memory (SoftPPO-LSTM) algorithm to intelligently select CB nodes for improving transmission efficiency. Simulation results show that the proposed OMRP improves network lifetime by 17% compared to benchmark routing protocols, while the SoftPPO-LSTM method for CB node selection achieves an 8.3% increase in throughput over benchmark algorithms. The results also reveal that the combined OMRP with the SoftPPO-LSTM method effectively mitigates hot spot problems and offers superior performance compared to traditional strategies.

Autonomous aerial vehicles (AAVs) have gained considerable attention as a platform for establishing aerial wireless networks and communications. However, the Line of Sight (LoS) dominance in air-to-ground (A2G) communications often leads to significant interference with terrestrial networks, reducing communication efficiency among terrestrial terminals. This article explores a novel uplink interference mitigation approach based on the collaborative beamforming (CB) method in multi-AAV network systems. Specifically, the AAV swarm forms an AAV-enabled virtual antenna array (VAA) to achieve the transmissions of gathered data to multiple base stations (BSs) for data backup and distributed processing. However, there is a tradeoff tradeoff between the effectiveness of CB-based interference mitigation and the energy conservation of AAVs. Thus, by optimizing the excitation current weights and hover position of AAVs as well as the sequence of data transmission to various BSs, we formulate an uplink interference mitigation multiobjective optimization problem (MOOP) to decrease interference affection, enhance transmission efficiency, and improve energy efficiency, simultaneously. In response to the computational demands of the formulated problem, we introduce an evolutionary computation method, namely chaotic nondominated sorting genetic algorithm II (CNSGA-II) with multiple improved operators. The proposed CNSGA-II efficiently addresses the formulated MOOP, outperforming several other comparative algorithms, as evidenced by the outcomes of the simulations. Moreover, the proposed CB-based uplink interference mitigation approach can significantly reduce the interference caused by AAVs to nonreceiving BSs.

To achieve ultrareliable and low-latency communication (URLLC) and support high density of wireless connections simultaneously, the sixth-generation Industrial Internet of Things (6G-IIoT) necessitates an expansion of antenna arrays and broader bandwidths, which suffers from high energy consumption. To address this issue, this article investigates a cell-free massive multiple-input-multiple-output (CF-mMIMO) system and designs an iterative search-based two-stage energy efficiency (EE) optimization algorithm for the uplink communication of the system. The first stage prioritizes reliability to ensure that all users meet the URLLC requirements regarding latency and reliability. The second stage maximizes the EE under URLLC-satisfied conditions. Considering that iterative search algorithms incur a high computational overhead and variable number of iterations, we further propose a convolutional neural network architecture (RACNN) to approximate an optimal resource allocation strategy and to realize the real-time and stable output. This structure extracts deep correlations among users from the global channel features. It takes strategies of multitask learning and weight loss adaptation to improve the model’s convergence speed. Furthermore, we employ deep transfer learning to adjust RACNN parameters to accommodate the potential of dynamic communication scenarios, thereby reducing the demand for training samples and training time overhead. Finally, the efficacy of the proposed algorithm, RACNN, and deep transfer learning is validated through experimental simulations.

This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems. By integrating core tenets, such as least privilege access, continuous verification, data confidentiality, and behavioral analytics into the design, training, and deployment of FMs, ZTFMs can enable secure, privacy-preserving AI across distributed, heterogeneous, and potentially adversarial IoT environments. We present the first structured synthesis of ZTFMs, identifying their potential to transform conventional trust-based IoT architectures into resilient, self-defending ecosystems. Moreover, we propose a comprehensive technical framework, incorporating federated learning (FL), blockchain-based identity management, micro-segmentation, and trusted execution environments (TEEs) to support decentralized, verifiable intelligence at the network edge. In addition, we investigate emerging security threats unique to ZTFM-enabled systems and evaluate countermeasures, such as anomaly detection, adversarial training, and secure aggregation. Through this analysis, we highlight key open research challenges in terms of scalability, secure orchestration, interpretable threat attribution, and dynamic trust calibration. This survey lays a foundational roadmap for secure, intelligent, and trustworthy IoT infrastructures powered by FMs.

In recent years, Federated Learning (FL) has emerged as a widely adopted privacy-preserving distributed training approach, attracting significant interest from both academia and industry. Research efforts have been dedicated to improving different aspects of FL, such as algorithm improvement, resource allocation, and client selection, to enable its deployment in distributed edge networks for practical applications. One of the reasons for the poor FL model performance is due to the worker dropout during training as the FL server may be located far away from the FL workers. To address this issue, an Hierarchical Federated Learning (HFL) framework has been introduced, incorporating an additional layer of edge servers to relay communication between the FL server and workers. While the HFL framework improves the communication between the FL server and workers, large number of communication rounds may still be required for model convergence, particularly when FL workers have non-independent and identically distributed (non-IID) data. Moreover, the FL workers are assumed to fully cooperate in the FL training process, which may not always be true in practical situations. To overcome these challenges, we propose a synthetic-data-empowered HFL framework that mitigates the statistical issues arising from non-IID local datasets while also incentivizing FL worker participation. In our proposed framework, the edge servers reward the FL workers in their clusters for facilitating the FL training process. To improve the performance of the FL model given the non-IID local datasets of the FL workers, the edge servers generate and distribute synthetic datasets to FL workers within their clusters. FL workers determine which edge server to associate with, considering the computational resources required to train on both their local datasets and the synthetic datasets. The simulation results show that an evolutionary equilibrium is reached where the FL workers do not have incentive to change their edge association strategies. Given this equilibrium, the FL workers facilitate the FL training of the edge servers that they associate with and be rewarded for their contributions. The proposed framework achieves higher FL model accuracy with an addition of 5% of synthetic data.

The growing adoption of electric buses (EBs) represents a significant step toward sustainable development. By utilizing Internet of Things (IoT) systems, charging stations can autonomously determine charging schedules based on real-time data. However, optimizing EB charging schedules remains a critical challenge due to uncertainties in travel time, energy consumption, and fluctuating electricity prices. Moreover, to address real-world complexities, charging policies must make decisions efficiently across multiple time scales and remain scalable for large EB fleets. In this article, we propose a hierarchical deep reinforcement learning (HDRL) approach that reformulates the original Markov decision process (MDP) into two augmented MDPs. To solve these MDPs and enable multitimescale decision-making, we introduce a novel HDRL algorithm, namely, double actor-critic multiagent proximal policy optimization enhancement (DAC-MAPPO-E). Scalability challenges of the double actor-critic (DAC) algorithm for large-scale EB fleets are addressed through enhancements at both decision levels. At the high level, we redesign the decentralized actor network and integrate an attention mechanism to extract relevant global state information for each EB, decreasing the size of neural networks. At the low level, the multiagent proximal policy optimization (MAPPO) algorithm is incorporated into the DAC framework, enabling decentralized and coordinated charging power decisions, reducing computational complexity and enhancing convergence speed. Extensive experiments with real-world data demonstrate the superior performance and scalability of DAC-MAPPO-E in optimizing EB fleet charging schedules.

Low Earth orbit (LEO) satellite networks are an important component of future 6G. However, due to the unique characteristics of the space environment—such as the complexity in modeling network states and the rapid dynamics of the network topology—existing routing methods often struggle to make appropriate routing decisions in the LEO satellite network context, which significantly limits network transmission performance. In this paper, we propose a dynamic satellite routing method based on deep graph attention and incremental evolution strategy (DGA-IES). Firstly, to address the challenge of accurately perceiving satellite network information, we introduce a topological perception learning model based on deep graph attention. By combining an enhanced message passing process with a self-attention mechanism, this model effectively captures complex features of the LEO network state, including inter-satellite connectivity relationships, as well as the resource states of satellites and links. Secondly, to tackle the problem of inefficient routing re-convergence in rapidly changing topologies, this paper integrates evolution strategies (ES) into deep reinforcement learning (DRL) approaches. We use the global parallel processing capabilities of ES to replace the sequential interactive proximal policy optimization (PPO) strategy in existing DRL. Moreover, we design an incremental evolutionary process based on satellite motion patterns, facilitating efficient routing convergence in highly dynamic satellite environments. Experimental results demonstrate that our DGA-IES approach enhances LEO network load balancing by reducing end-to-end (E2E) network latency by 10.3% 58.1%, decreasing packet loss by 3.8% 20.0%, and improving throughput by 11.1% 57.0% compared with the benchmark approaches.

In this work, we consider the integration of energy harvesting (EH) and semantic communication strategies in resource-constrained Internet of Things (IoT) systems. The system empowers IoT devices to harvest energy from a base station, utilizing this harvested energy for the extraction and transmission of semantic information (e.g., scene graphs). To maximize the total transmission of image data or scene graphs to the central station, we formulate a comprehensive problem that jointly optimizes the EH duration, original image selection, transmit power, and channel allocation to IoT devices. The challenges arising from the dynamic environments and uncertain system parameters are effectively tackled by policy-based deep reinforcement learning algorithms, i.e., advantage actor-critic (A2C) and proximal policy optimization (PPO). Simulation results are implemented on the real data set clearly showing the superior performance achieved by our proposed algorithms compared to the baseline schemes. Notably, our approach enables IoT devices to transmit a greater number of original images and scene graphs with increased triplets to the central station, as highlighted in the simulation outcomes. This phenomenon showcases the potential of our strategy to enhance the capabilities of IoT systems in dynamic environments.

Hybrid Language Models (HLMs) are inference-time architectures that combine the low-latency efficiency of Small Language Models (SLMs) on clients (edge devices) with the high accuracy of Large Language Models (LLMs) in centralized servers. Unlike traditional end-to-end LLM inference, HLMs aim to reduce latency and communication by selectively invoking LLMs only when the local SLM’s predictions are uncertain—that is, when the model exhibits low confidence or high entropy in its token-level probability distribution. However, when the SLM encounters ambiguous or low-confidence predictions during inference, it must offload token-level probability distributions to the LLM for refinement. This frequent offloading leads to substantial communication overhead, particularly in bandwidth-constrained environments. To address this challenge, we propose FedHLM, a communication-efficient HLM framework that integrates uncertainty-aware inference with Federated Learning (FL). The key innovation lies in collaboratively learning token-level uncertainty thresholds that determine when SLM predictions require LLM assistance. Instead of relying on static or hand-tuned thresholds, FedHLM uses FL to enable distributed threshold optimization across clients while preserving data privacy. Additionally, embedding-based token representations are employed to facilitate semantic similarity comparisons during Peer-to-Peer (P2P) resolution, allowing clients to reuse tokens inferred by similar peers without efficiently involving the LLM. Moreover, we propose hierarchical model aggregation as a strategy to reduce redundant token transmissions. At the edge server level, client updates are aggregated to refine local routing policies, while global coordination across clusters further synchronizes decision boundaries. This layered approach ensures that repeated uncertainty patterns are captured and resolved locally, significantly reducing unnecessary LLM queries. Extensive simulations on large-scale news classification tasks demonstrate that FedHLM achieves over 95% reduction in LLM transmissions with negligible accuracy loss, highlighting its potential for scalable and efficient edge-Artificial Intelligence (AI) deployment.

In existing deep learning-based semantic communication systems, centralized training of semantic models brings a risk of privacy leakage, whereas distributed training imposes a huge computational burden on user equipments (UEs). To address these challenges, we propose a hybrid federated learning (Hybrid-FL) framework to alleviate the computational burden on UEs while protecting the user privacy. Specifically, each UE uploads local gradients and semantic symbols to the base station for the collaborative training of global and local semantic models. Furthermore, we propose a joint communication and computation scheme for supporting the model aggregation and semantics transmission. To gain deep insights, we expose the joint impact of communication and computation on the convergence behavior of Hybrid-FL by deriving an upper bound. Then, we formulate a mixed-integer nonlinear programming problem to improve the convergence performance of Hybrid-FL, which is then effectively solved by using our proposed algorithm that developed based on alternating and matching theory. Experimental results demonstrate that Hybrid-FL outperforms conventional FL by achieving a 20% accuracy gain and a 80% latency reduction.

Autonomous aerial vehicle (AAV)-assisted mobile edge computing (MEC) and data collection (DC) have been popular research issues. Different from existing works that consider MEC and DC scenarios separately, this article investigates a multi-AAV-assisted joint MEC-DC system. Specifically, we formulate a joint optimization problem to minimize the MEC latency and maximize the collected data volume. This problem can be classified as a nonconvex mixed integer programming problem that exhibits long-term optimization and dynamics. Thus, we propose a deep reinforcement learning-based approach that jointly optimizes the AAV movement, user transmit power, and user association in real time to solve the problem efficiently. Specifically, we reformulate the optimization problem into an action space-reduced Markov decision process (MDP) and optimize the user association by using a two-phase matching-based association (TMA) strategy. Subsequently, we propose a soft actor-critic (SAC)-based approach that integrates the proposed TMA strategy (SAC-TMA) to solve the formulated joint optimization problem collaboratively. Simulation results demonstrate that the proposed SAC-TMA is able to coordinate the two subsystems and can effectively reduce the system latency and improve the DC volume compared with other benchmark algorithms.

With the rapid advancements in wireless communication fields, including low-altitude economies, 6G, and Wi-Fi, the scale of wireless networks continues to expand, accompanied by increasing service quality demands. Traditional deep reinforcement learning (DRL)-based optimization models can improve network performance by solving non-convex optimization problems intelligently. However, they heavily rely on online deployment and often require extensive initial training. Online DRL optimization models typically make accurate decisions based on current channel state distributions. When these distributions change, their generalization capability diminishes, which hinders the responsiveness essential for real-time and high-reliability wireless communication networks. Furthermore, different users have varying quality of service (QoS) requirements across diverse scenarios, and conventional online DRL methods struggle to accommodate this variability. Consequently, exploring flexible and customized AI strategies is critical. We propose a wireless network intent (WNI)-guided trajectory generation model based on a generative diffusion model (GDM). This model can be generated and fine-tuned in real time to achieve the objective and meet the constraints of target intent networks, significantly reducing state information exposure during wireless communication. Moreover, The WNI-guided DRL optimization trajectory generation can be customized to address differentiated QoS requirements, enhancing the overall quality of communication in future intelligent networks. Extensive simulation results demonstrate that our approach achieves greater stability in spectral efficiency variations and outperforms traditional DRL optimization models in dynamic communication systems.

Large language models (LLMs) have demonstrated remarkable capacities on various tasks, and integrating the capacities of LLMs into the Internet of Things (IoT) applications has drawn much research attention recently. Due to security concerns, many institutions avoid accessing state-of-the-art commercial LLM services, requiring the deployment and utilization of open-source LLMs in a local network setting. However, open-source LLMs usually have more limitations regarding their performance, such as their arithmetic calculation and reasoning capacities, and practical systems of applying LLMs to IoT have yet to be well-explored. Therefore, we propose an LLM-based Generative IoT (GIoT) system deployed in the local network setting in this study. To alleviate the limitations of LLMs and provide service with competitive performance, we apply prompt engineering methods to enhance the capacities of the open-source LLMs, design a Prompt Management Module and a Postprocessing Module to manage the tailored prompts for different tasks and process the results generated by the LLMs. To demonstrate the effectiveness of the proposed system, we discuss a challenging table question answering (Table-QA) task as a case study of the proposed system, as tabular data is usually more challenging than plaintext because of their complex structures, heterogeneous data types and sometimes huge sizes. We conduct comprehensive experiments on the two popular Table-QA data sets, and the results show that our proposal can achieve competitive performance compared with state-of-the-art LLMs, demonstrating that the proposed LLM-based GIoT system can provide competitive performance with tailored prompting methods and is easily extensible to new tasks without training.

Unmanned underwater vehicles (UUVs) have been widely used in various ocean applications, such as underwater exploration and data collection. And the underwater pursuit-evasion game (UPEG) is the key to efficient implementation of other tasks, holding significant research value. However, testing the UPEG task in real ocean environment is both costly and risky, and currently, UUV control algorithms that rely on specific environmental models struggle to complete the complicated UPEG task. To address above challenge, we propose UPEGSim, an UUV simulator specifically designed for the UPEG task. Built through Gazebo and robot operating system, UPEGSim provides a reinforcement learning (RL) environment to train UUVs for improving the intelligent performance in the UPEG task. Furthermore, we propose an efficient UPEG training framework (ETFDU), which includes multiagent decentralized training and execution techniques, scene transfer training methods, and offline RL techniques based on decision transformer, to facilitate efficient UUV training. Through training on the UPEG task in UPEGSim, we validate the effectiveness and feasibility of the proposed UPEGSim simulator and the ETFDU training framework.

Non-Terrestrial Networks (NTNs), as one core infrastructure of the sixth-generation (6G) communication technology, integrate heterogeneous nodes, such as High Earth Orbit (HEO) satellites, to achieve three-dimensional ubiquitous connectivity. However, NTNs face with spectrum scarcity, imposing stringent demands on spectral efficiency and interference management. To address these challenges, we propose a NOMA-oriented spectrum sensing technique for uplink scenarios, where High-Altitude Platforms (HAPs) serve as dynamic aerial nodes for opportunistic transmission within HEO coverage. Specifically, we derive multi-user sensing thresholds to optimize detection accuracy and suppress false alarms. Numerical simulations demonstrate the technique achieves a 33.5% throughput gain over benchmarks at 10 dB and maintains satisfactory performance across PUs’ varying elevation angles and transmission willingness.

Real-time and contactless monitoring of vital signs, such as respiration and heartbeat, alongside reliable communication, is essential for modern healthcare systems, especially in remote and privacy-sensitive environments. Traditional wireless communication and sensing networks fall short in meeting all the stringent demands of eHealth, including accurate sensing, high data efficiency, and privacy preservation. To overcome the challenges, we propose a novel integrated sensing, computing, and semantic communication (ISCSC) framework. In the proposed system, a service robot utilises radar to detect patient positions and monitor their vital signs, while sending updates to the medical devices. Instead of transmitting raw physiological information, the robot computes and communicates semantically extracted health features to medical devices. This semantic processing improves data throughput and preserves the clinical relevance of the messages, while enhancing data privacy by avoiding the transmission of sensitive data. Leveraging the estimated patient locations, the robot employs an interacting multiple model (IMM) filter to actively track patient motion, thereby enabling robust beam steering for continuous and reliable monitoring. We then propose a joint optimisation of the beamforming matrices and the semantic extraction ratio, subject to computing capability and power budget constraints, with the objective of maximising both the semantic secrecy rate and sensing accuracy. Simulation results validate that the ISCSC framework achieves superior sensing accuracy, improved semantic transmission efficiency, and enhanced privacy preservation compared to conventional joint sensing and communication methods.

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can expand the coverage of mobile edge computing (MEC) services by reflecting and transmitting signals simultaneously, enabling full-space coverage. The orientation of the STAR-RIS plays a crucial role in optimizing the gain of received and transmitted signals, and a rotatable STAR-RIS offers potential enhancement for MEC systems. This article investigates a rotatable STAR-RIS-assisted MEC system, operated under three protocols, namely energy splitting (ES), mode switching, and time switching. The goal is to minimize energy consumption for multiple moving user devices (UDs) through the joint optimization of STAR-RIS configurations, orientation, computation resource allocation, transmission power, and task offloading strategies. Considering the mobility of UDs, we model the original optimization problem as a sequential decision-making process across multiple time slots. The high-dimensional, highly coupled, and nonlinear nature makes it a challenging nonconvex decision-making problem for traditional optimization algorithms. Therefore, a deep reinforcement learning (DRL) approach is employed, specifically utilizing soft actor-critic algorithm to train the DRL model. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in both convergence speed and energy efficiency, while reducing energy consumption by up to 52.7% compared to the fixed STAR-RIS scheme. Among three operating protocols, the ES yields the best performance.

Fuzz testing is an dynamic program analysis technique designed for discovering vulnerabilities in IoT systems. The core goal is to deliberately feed maliciously crafted inputs into an IoT device or service, triggering vulnerabilities such as system crashes, buffer overflow exploits, and memory corruption, etc. Efficiently generating malicious inputs remains challenging, with leading methods often relying on randomly mutating existing valid inputs. In this work, we propose to adopt fine-tuned large language models (FuzzCoder) to learn patterns in the input files from successful attacks to guide future fuzzing explorations. Specifically, we develop a framework that leverages code LLMs to guide the mutation process to perform meaningful input mutations. We formulate the mutation process as the sequenceto-sequence modeling, where LLM receives a sequence of bytes and outputs the mutated byte sequence. FuzzCoder is fine-tuned on our created instruction dataset (FuzzInstruct), where the successful fuzzing history is collected from the heuristic fuzzing tool. FuzzCoder can predict mutation positions and strategies for input files to trigger abnormal behaviors of the program. Most importantly, the experiment reveals results that FuzzCoder achieves better fuzzing performance compared to traditional and other AFL-based fuzzers, such as AFL, AFL++, AFLSmart, etc. On average, FuzzCoder achieves an improvement in code coverage of more than 20%, along with a significant increase in the number of crashes. 1

With the advancements of generative artificial intelligence (GenAI) models, their capabilities are expanding significantly beyond content generation and the models are increasingly being used across diverse applications. Particularly, GenAI shows great potential in addressing challenges in the electric vehicle (EV) ecosystem ranging from charging management to cyber-attack prevention. In this article, we specifically consider Internet of Electric Vehicles (IoEV) and we categorize GenAI for IoEV into four different layers, namely, EV’s battery layer, individual EV layer, smart grid layer, and security layer. We introduce various GenAI techniques used in each layer of IoEV applications. Subsequently, public datasets available for training the GenAI models are summarized. Finally, we provide recommendations for future directions. This survey not only categorizes the applications of GenAI in IoEV across different layers but also serves as a valuable resource for researchers and practitioners by highlighting the design and implementation challenges within each layer. Furthermore, it provides a roadmap for future research directions, enabling the development of more robust and efficient IoEV systems through the integration of advanced GenAI techniques.

Mobile crowdsensing (MCS) is a novel sensing paradigm by utilizing mobile users (MUs) to collect data from environment. Considering the finite sensing and computing resources of MUs, it is crucial to inspire MUs to take part in crowdsensing willingly. In this study, a multiagent-deep-reinforcement-learning (DRL)-based incentive mechanism is investigated to tackle the joint data sensing and computing issues. Specifically, due to the heterogeneity of sensing tasks, multiple MCS platforms (MCPs) motivate MUs to participate in different tasks. The interaction between MCPs and MUs is modeled as a multileader-multifollower Stackelberg game with Stackelberg equilibrium proved by derivation. Moreover, the Stackelberg game is transformed as a Markov decision process (MDP) to deal with a multiagent DRL method without any prior knowledge. Due to the continuous high-dimensional action space of multiple MCPs and MUs, a multiagent double actors deep deterministic policy gradient (MA-DADDPG) algorithm is proposed to obtain the optimal sensing data size, computing resource, and incentive payment policies. Extensive simulation results illustrate the effectiveness of the proposed crowdsensing incentive mechanism.

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an autonomous aerial vehicle (AAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a AAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by AAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different AAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed semi-synchronous FL with cross-sharpness and layer-freezing (SFedXL), tailored for a AAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a tradeoff of increased local computation latency.

Mobile crowdsensing (MCS) is an emerging technology, which provides a promising paradigm for completing complex sensing tasks. While existing studies for MCS mainly focus on designing incentive mechanisms to attract more participants or optimizing task allocation to maximize profit, the freshness of information, known as Age of Information (AoI), has been largely overlooked. In MCS systems, some Point of Interests (PoIs) need to be monitored through sampling by participants. High-frequency sampling can effectively ensure AoI performance, which also imposes significant costs on participants. Therefore, it is necessary to allocate appropriate sampling tasks and design the corresponding sample cycles and prices for participants. In this article, we address the joint problem of incentive mechanism and task allocation. First, we adopt the contract theory to model the incentive mechanism, where the crowdsensing platform (CP) offers a set of cycle-price combinations to participants. We establish the necessary and sufficient conditions for the feasibility of the contract and subsequently derive the optimal contract structure. Second, subject to the derived contract structure, we determine the optimal task allocation under specific conditions. For more general situations, we propose an iterative algorithm, which is based on pair switching with a proven convergence guarantee. Finally, the simulation results demonstrate the efficiency of the proposed contract-based algorithm, which also outperforms other incentive mechanisms.

Inadequate resource coordination and control can result in poor quality of experience (QoE) for user devices in heterogeneous edge-enabled cyber-physical systems. Unfortunately, in a cooperative edge network, existing studies have rarely jointly optimized communication, computing resources, and batch size for QoE guarantee when controlling task offloading. To this end, we investigate the problem of harnessing bandwidth, computation, and batch size for fair quality of experience (HARBOR) in a practical collaborative edge-AI environment, where UEs have different accuracy requirements of inference services and edge devices possess different batch processing capabilities. Specifically, we introduce the task completion efficiency as the task-completion-time-to-deadline ratio to quantify individual QoE. Then, we formulate the problem HARBOR as a mixed integer nonlinear programming with constraints of accuracy, bandwidth, computation, task hard deadlines and so on. The objective is to minimize the maximum task completion efficiency among all tasks to achieve task-level fairness. After providing the NP-hardness proof for HARBOR, we then devise an efficient scheme named e-HARBOR with a competitive ratio guarantee, to solve the decoupled sub-problems of HARBOR with calibrated long short-term memory network for resource prediction. Both testbed and simulation experiments evidently demonstrate that the proposed scheme works efficiently and scales well compared to baselines.

The advent of ultra-massive multiple-input-multiple-output (UM-MIMO) systems holds great promise for next-generation communications, yet their channels exhibit hybrid far- and near- field beam-squint (HFBS) effect. In this paper, we not only overcome but also harness the HFBS effect to propose an integrated location sensing and communication (ILSC) framework. During the uplink training stage, user terminals (UTs) transmit reference signals for simultaneous channel estimation and location sensing. This stage leverages an elaborately designed hybrid-field projection matrix to overcome the HFBS effect and estimate the channel in compressive manner. Subsequently, the scatterers’ locations can be sensed from the spherical wavefront based on the channel estimation results. By treating the sensed scatterers as virtual anchors, we employ a weighted least-squares approach to derive the UT’s location. Moreover, we propose an iterative refinement mechanism, which utilizes the accurately estimated time difference of arrival (TDoA) of multipath components to enhance location sensing precision. In the following downlink data transmission stage, we leverage the acquired location information to further optimize the hybrid beamformer, which combines the beam broadening and focusing to mitigate the spectral efficiency degradation resulted from the HFBS effect. Extensive simulation experiments demonstrate that the proposed ILSC scheme has superior location sensing and communication performance than conventional methods.

Energy efficiency (EE) optimization has attracted significant research attention for implementing green communications. With cost-effective and low-power advantages, intelligent reflecting surface (IRS) and hybrid analog-digital transceiver have recently emerged as two promising technologies of next-generation green wireless systems. In this paper, we propose a comprehensive framework for EE optimization in four types of IRS-aided hybrid analog-digital multiuser multiple-input multiple-output communication systems, including the uplink (UL) systems under the sum power and box eigenvalue constraints as well as the per-radio-frequency chain power constraints (PRPCs), and the downlink (DL) systems under the sum power constraint and the PRPCs. This framework proposes a unified design methodology to these four considered systems by separating the optimization of analog and digital matrix variables. Specifically, for the UL EE maximization problems, we firstly propose a channel alignment based algorithm to separately optimize the analog precoders at users, the analog combiner at the base station and the IRS reflecting matrix, whose computational complexity is significantly reduced as compared with the traditional alternating optimization algorithm. Then, by introducing the auxiliary variables and exploiting the Karush-Kuhn-Tucker conditions based algorithm, the optimal digital precoders at users are obtained in closed forms. Furthermore, the intractable DL EE optimization can be equivalently transformed into its virtual UL counterpart using the DL-UL duality, leading to the general applicability of the proposed framework. Extensive simulations reveal that the proposed algorithm attains the almost identical EE performance to the traditional benchmarks with a lower computational complexity.

Wireless networked control systems (WNCSs) are critical to Industry 4.0, enabling applications like drone swarms and autonomous robots. The tight interdependence between communication and control demands integrated design, yet traditional approaches treat them separately, leading to inefficiencies. Existing codesign methods often rely on simplified models for single-loop or independent multi-loop systems, overlooking the complexities of large-scale WNCSs. These include coupled control loops, time-correlated wireless channels, sensing-control trade-offs, and computational challenges. To address these challenges, we propose a practical WNCS model that captures correlated dynamics among spatially distributed sensors and actuators sharing limited wireless resources over multi-state Markov block-fading channels. To solve the resulting high-dimensional codesign problem, we develop a deep reinforcement learning (DRL) algorithm that scales efficiently by managing hybrid action spaces, capturing communication-control dependencies, and maintaining robust performance under time-correlated dynamics and resource constraints. Simulations demonstrate that our DRL approach outperforms benchmarks, providing a scalable and effective solution for large-scale industrial WNCSs.

To achieve stringent performance requirements in next generation wireless networks, such as ultra-high data rates, ubiquitous connectivity, and extremely high reliability, this paper proposes a radically novel rate splitting assisted dual-polarized stacked metasurface (RS-DPSM) transceiver architecture. In this architecture, a multi-layer dual-polarized metasurface is stacked at the active antennas and its two inherent polarizations are implemented to enable RS’s common and private messages in parallel. In sharp contrast to the conventional multiple-input multiple-output (MIMO) and metasurface-based transceiver designs, our proposed transceiver is capable of enhancing the channel capacity and introducing multi-dimensional degrees of freedom (DoFs) in the power, spatial, and polarization domains, thus enabling multi-functional, broad-spectrum, and all-time/domain/space communications without requiring massive radio-frequency (RF) chains. In addition, we derive new analytical expressions for the upper bounds of RS-DPSM transceiver’s channel capacity and ergodic sum rate, and provide some key insights. To highlight its potential benefits, we apply the proposed RS-DPSM transceiver to anti-jamming communications, and formulate a generalized sum rate maximization problem under the jammer’s imperfect angular channel state information and unknown cross-polarization discrimination. To enable an efficient resource management under the above practical conditions, we present a low-complexity optimization framework by leveraging the discretization method, properties of the quadratic function, reduced-majorization-minimization algorithm, and block successive upper-bound minimization, which admit the semi-closed-form solutions. Finally, our numerical simulations verify the superiority of our proposed transceiver architecture and optimization framework over key benchmarks.

The combination of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) and an unmanned aerial vehicle (UAV) can further improve channel quality and extend coverage. However, the high-quality air-to-ground link is more vulnerable to eavesdropping by adversaries. In this paper, we investigate STAR-RIS-assisted covert communication in UAV non-orthogonal multiple access (NOMA) networks with a warden Willie, where Alice intends to transmit the covert signal to a near user Bob under the cover of a far user Carol via STAR-RIS. We aim to maximize the covert transmission rate by jointly optimizing the active and passive beamforming as well as the UAV location. The error detection probability and optimal detection threshold for Willie are first derived to obtain an analytic solution for the minimum detection error probability. Then, an alternating optimization algorithm is proposed to maximize the covert transmission rate under the condition of guaranteeing the communication of Carol and satisfying the covertness constraint of Bob. Specifically, the nonconvex problem is decomposed into three sub-problems by block coordinate descent, which are then solved using semidefinite relaxation and successive convex approximation. Finally, simulation results are presented to demonstrate the effectiveness of the proposed covert communication scheme for STAR-RIS assisted UAV air-ground networks.

Near-space airship-borne communication network is recognized to be an indispensable component of the future integrated ground-air-space network thanks to airships’ advantage of long-term residency at stratospheric altitudes, but it urgently needs reliable and efficient Airship-to-X link. To improve the transmission efficiency and capacity, this paper proposes to integrate semantic communication with massive multiple-input multiple-output (MIMO) technology. Specifically, we propose a deep joint semantic coding and beamforming (JSCBF) scheme for airship-based massive MIMO image transmission network in space, in which semantics from both source and channel are fused to jointly design the semantic coding and physical layer beamforming. First, we design two semantic extraction networks to extract semantics from image source and channel state information, respectively. Then, we propose a semantic fusion network that can fuse these semantics into complex-valued semantic features for subsequent physical-layer transmission. To efficiently transmit the fused semantic features at the physical layer, we then propose the hybrid data and model-driven semantic-aware beamforming networks. At the receiver, a semantic decoding network is designed to reconstruct the transmitted images. Finally, we perform end-to-end deep learning to jointly train all the modules, using the image reconstruction quality at the receivers as a metric. The proposed deep JSCBF scheme fully combines the efficient source compressibility and robust error correction capability of semantic communication with the high spectral efficiency of massive MIMO, achieving a significant performance improvement over existing approaches.

Coordinated multi-base station (BS) transmission has emerged as a fundamental access technology to augment network capability and improve spectrum efficiency. However, the computation-intensive feedback of channel state information (CSI) poses significant challenges in determining physical-layer parameters for coordinated BSs. In this paper, we investigate a feedback-free mechanism that leverages fixed precoding matrix indicator (PMI), rank indicator (RI), and channel quality indicator (CQI) for coordinated BS transmission over a fully-decoupled radio access network (FD-RAN). Aiming to maximize user equipment (UE) throughput without CSI feedback, we calculate an optimal feedback-free parameter across spatial, frequency, and time domains only through UE geolocations. First, to determine MIMO transmission layer and precoding strategy in the spatial domain, we introduce a hierarchical reinforcement learning (HRL) framework to jointly select PMI and RI for coordinated BSs. Subsequently, for designing a more fine-grained subband transmission, transformer module is employed to capture the subcarrier correlations within OFDM symbols. Finally, given the unpredictable channel variations, we leverage a diffusion model to generate representative channel for fixed PMI, RI, and CQI over time-varied networks. Simulations demonstrate that 2 BSs feedback-free transmission can enhance 13% throughput compared with 1 BS CLSM transmission, which provides a design principle for next-generation transceiver technologies.

Over-the-air computation (AirComp) has emerged as an essential approach for enabling communication-efficient federated learning (FL) over wireless networks. Nonetheless, the inherent analog transmission mechanism in AirComp-based FL (AirFL) intensifies challenges posed by potential Byzantine attacks. In this paper, we propose a novel Byzantine-robust FL paradigm for over-the-air transmissions, referred to as federated learning with secure adaptive clustering (FedSAC). FedSAC aims to protect a portion of the devices from attacks through zero trust architecture (ZTA) based Byzantine identification and adaptive device clustering. By conducting a one-step convergence analysis, we theoretically characterize the convergence behavior with different device clustering mechanisms and uneven aggregation weighting factors for each device. Building upon our analytical results, we formulate a joint optimization problem for the clustering and weighting factors in each communication round. To facilitate the targeted optimization, we propose a dynamic Byzantine identification method using historical reputation based on ZTA. Furthermore, we introduce a sequential clustering method, transforming the joint optimization into a weighting optimization problem without sacrificing the optimality. To optimize the weighting, we capitalize on the penalty convex-concave procedure (P-CCP) to obtain a stationary solution. Numerical results substantiate the superiority of the proposed FedSAC over existing methods in terms of both test accuracy and convergence rate.

The future sixth-generation (6G) of wireless networks is expected to surpass its predecessors by offering ubiquitous coverage through integrated air-ground deployments in both communication and computing domains. In such networks, aerial platforms, such as unmanned aerial vehicles (UAVs), conduct artificial intelligence (AI) computations based on multi-modal data to support diverse applications including surveillance and environment construction. However, these multi-domain inference and content generation tasks require large AI models, demanding powerful computing capabilities and finely tuned inference models trained on rich datasets, thus posing significant challenges for UAVs. To tackle this problem, we propose an integrated air-ground edge-cloud model framework, in which UAVs serve as edge nodes for data collection and small model computation. Through wireless channels, UAVs collaborate with ground cloud servers providing large model computation and model updating for edge UAVs. With limited wireless communication bandwidth, the proposed framework faces the challenge of information exchange scheduling between the edge UAVs and the cloud server. To tackle this, we present joint task allocation, transmission resource allocation, transmission data quantization design, and edge model update design to enhance the inference accuracy of the integrated air-ground edge-cloud model evolution framework by mean average precision (mAP) maximization. A closed-form lower bound on the mAP of the proposed framework is derived based on the mAP of the edge model and mAP of the cloud model, and the solution to the mAP maximization problem is optimized accordingly. Simulations, based on results from vision-based classification experiments, consistently demonstrate that the mAP of the proposed integrated air-ground edge-cloud model evolution framework outperforms both a centralized cloud model framework and a distributed edge model framework across various communication bandwidths and data sizes.

Distributed Artificial Intelligence-Generated Content (AIGC) has attracted significant attention, but two key challenges remain: maximizing subjective Quality of Experience (QoE) and improving energy efficiency, which are particularly pronounced in widely adopted Generative Diffusion Model (GDM)-based image generation services. In this paper, we propose a novel user-centric Interactive AI (IAI) approach for service management, with a distributed GDM-based AIGC framework that emphasizes efficient and cooperative deployment. The proposed method restructures the GDM inference process by allowing users with semantically similar prompts to share parts of the denoising chain. Furthermore, to maximize the users' subjective QoE, we propose an IAI approach, i.e., Reinforcement Learning With Large Language Models Interaction (RLLI), which utilizes Large Language Model (LLM)-empowered generative agents to replicate users interactions, providing real-time and subjective QoE feedback aligned with diverse user personalities. Lastly, we present the GDM-based Deep Deterministic Policy Gradient (G-DDPG) algorithm, adapted to the proposed RLLI framework, to allocate communication and computing resources effectively while accounting for subjective user traits and dynamic wireless conditions. Simulation results demonstrate that G-DDPG improves total QoE by 15% compared with the standard DDPG algorithm.

Smart railways integrate advanced information technologies into railway operating systems to improve efficiency and reliability. Although the development of the fifth generation (5G) has enhanced railway services, future smart railways require ultra-high speeds, ultra-low latency, ultra-high security, full coverage, and ultra-high positioning accuracy, which 5G cannot fully meet. Therefore, the sixth generation (6G) is envisioned to provide green and efficient all-day operations, strong information security, fully automatic driving, and low-cost intelligent maintenance. To achieve these requirements, we propose an integrated network architecture leveraging communications, computing, edge intelligence, and caching in railway systems. We have conducted in-depth investigations on key enabling technologies for reliable transmissions and wireless coverage. For high-speed mobile scenarios, we propose an artificial intelligence (AI)-enabled cross-domain channel modeling and orthogonal time–frequency space–time spread multiple access mechanism to alleviate the conflict between limited spectrum availability and massive user access. The roles of blockchain, edge intelligence, and privacy technologies in endogenously secure rail communications are also evaluated. We further explore the application of emerging paradigms such as integrated sensing and communications (SACs), AI-assisted Internet of Things (IoT), semantic communications (SCs), and digital twin (DT) networks for railway maintenance, monitoring, prediction, and accident warning. Finally, possible future research and development directions are discussed. © 2026 IEEE

In ground-air networks, dual-function radar and communication (DFRC) enables a base station (BS) to sense and send communication signals to unmanned aerial vehicles (UAVs) simultaneously, which has enormous potential. The emphasis of this letter is on the design of DFRC waveform for ground-air system under inaccurate target angle. The desired covariance matrix is considered to have the best radar performance in the presence of inaccurate target angle and the waveform design objective is to make the corresponding covariance matrix approximated to it. The constraints conclude multi-user interference (MUI) energy for high quality of communication and constant modulus for avoiding signal distortion. To address the problem that minimizes the covariance matrix difference under the constraints, we propose a block coordinate descent (BCD) method. Moreover, to ensure the problem feasible, we design an initial value acquisition strategy using bisection-based alternating direction method of multipliers (ADMM). Numerical results indicate that better communication and radar performance are achieved by the proposed method compared with existing methods.

A multi-tenant metaverse enables multiple users in a common virtual world to interact with each other online. Information sharing will occur when interactions between a user and the environment are multicast to other users by an interactive metaverse (IM) service. However, ineffective information-sharing strategies intensify competitions among users for limited resources in networks, and fail to interpret optimization intent prompts conveyed in high-level natural languages, ultimately diminishing user immersion. In this paper, we explore reliable information sharing in a multi-tenant metaverse with time-varying resource capacities and costs, where IM services are unreliable and alter the volumes of data processed by them, while the service provider dynamically adjusts global intent to minimize multicast delays and costs. To this end, we first formulate the information sharing problem as a Markov decision process and show its NP-hardness. Then, we propose a learning-based system GTP, which combines the proximal policy optimization reinforcement learning with feature extraction networks, including graph attention network and gated recurrent unit, and a Transformer encoder for multi-feature comparison to process a sequence of incoming multicast requests without the knowledge of future arrival information. The GTP operates through three modules: a deployer that allocates primary and backup IM services across the network to minimize a weighted goal of server computation costs and communication distances between users and services, an intent extractor that dynamically infers provider intent conveyed in natural language, and a router that constructs on-demand multicast routing trees adhering to users, the provider, and network constraints. We finally conduct theoretical and empirical analysis on the proposed algorithms for the system. Experimental results show that the proposed algorithms are promising, and superior to their comparison baseline algorithms.

In edge computing, energy-limited distributed edge clients present challenges such as heterogeneity, high energy consumption, and security risks. Traditional blockchain-based federated learning (BFL) struggles to address all three of these challenges simultaneously. This article proposes a Graph-Partitioning Multi-Granularity Federated Learning method on a consortium blockchain, namely GP-MGFL. To reduce the overall communication overhead, we adopt a balanced graph partitioning algorithm while introducing observer and consensus nodes. This method groups clients to minimize high-cost communications and focuses on the guidance effect within each group, thereby ensuring effective guidance with reduced overhead. To fully leverage heterogeneity, we introduce a cross-granularity guidance mechanism. This mechanism involves fine-granularity models guiding coarse-granularity models to enhance the accuracy of the latter models. We also introduce a credit model to adjust the contribution of models to the global model dynamically and to dynamically select leaders responsible for model aggregation. Finally, we implement a prototype system on real physical hardware and compare it with several baselines. Experimental results show that the accuracy of the GP-MGFL algorithm is 5.6% higher than that of ordinary BFL algorithms. In addition, compared to other grouping methods, such as greedy grouping, the accuracy of the proposed method improves by about 1.5%. In scenarios with malicious clients, the maximum accuracy improvement reaches 11.1%. We also analyze and summarize the impact of grouping and the number of clients on the model, as well as the impact of this method on the inherent security of the blockchain itself.

While diffusion models have demonstrated remarkable success in computer vision tasks, their deployment in Internet of Things environments remains challenging. Edge devices face significant constraints in computational resources and must adapt to dynamic operating conditions. To address these limitations, we propose a novel system that accelerates AIgenerated content (AIGC) collaborative inference in dynamic edge networks. The proposed system introduces a multi-exit vision transformer-based U-Net architecture that enables efficient processing through adaptive exit point selection during the diffusion process, optimizing the trade-off between inference accuracy and computational efficiency. To optimize device-level operations, we develop an innovative generative AI-assisted reinforcement learning framework that determines optimal exit selection and offloading strategies to maximize generation quality and inference speed. Furthermore, we design a fine-tuning approach with policy reuse mechanisms that facilitates rapid reinforcement learning algorithm deployment across diverse environments. Extensive experimental evaluations demonstrate that our system outperforms existing algorithms in terms of balancing inference latency and generation quality, while also exhibiting improved adaptability to environmental variations.

Flexible intelligent metasurfaces (FIMs) show great potential for improving the wireless network capacity in an energy-efficient manner. An FIM is a soft array consisting of several low-cost radiating elements. Each element can independently emit electromagnetic signals, while flexibly adjusting its position even perpendicularly to the overall surface to ‘morph’ its 3D shape. More explicitly, compared to a conventional rigid antenna array, an FIM is capable of finding an optimal 3D surface shape that provides improved signal quality. In this paper, we study point-to-point multiple-input multiple-output (MIMO) communications between a pair of FIMs. In order to characterize the capacity limits of FIM-aided MIMO transmissions over frequency-flat fading channels, we formulate a transmit optimization problem for maximizing the MIMO channel capacity by jointly optimizing the 3D surface shapes of the transmitting and receiving FIMs as well as the MIMO transmit covariance matrix, subject to the total transmit power constraint and to the maximum perpendicular morphing range of the FIM. To solve this problem, we develop an efficient block coordinate descent (BCD) algorithm. The BCD algorithm iteratively updates the 3D surface shapes of the FIMs and the transmit covariance matrix, while keeping the other fixed, to find a locally optimal solution. Numerical results verify that FIMs can achieve higher MIMO capacity than that of the conventional rigid arrays. In particular, the MIMO channel capacity can be doubled by the proposed BCD algorithm under some setups.

Reconfigurable intelligent surface (RIS) has gained much attention as a cost-effective solution to enhance connectivity and coverage in massive machine-type communication. However, the passive nature of RIS poses fundamental challenges to decoupling and estimating base station (BS)-RIS and RIS-device channels, as well as identifying active devices. To effectively tackle this issue, we cast the joint channel estimation and activity detection for RIS-assisted Internet-of-Things networks as a tensor-based two-layer problem by exploiting the channel sparsity and a multi-frame pilot training structure. The first layer involves the Canonical Polyadic (CP) decomposition of a third-order tensor observation, while the second layer addresses compressive sensing (CS)-based simple measurement vector (SMV) and multiple measurement vector (MMV) problems. Then, by leveraging the Bayesian inference framework, we propose a tensor-based approximate message passing (TAMP) algorithm to estimate one-hop BS-RIS channel, one-hop RIS-device channels, and active IoT devices simultaneously. Furthermore, we conduct the state evolution (SE) analysis of TAMP to theoretically characterize its MSE. Numerical results corroborate the superior estimation and detection performance of TAMP and demonstrate that our SE analysis perfectly predicts the actual MSE.

As an important part of underwater optical technology, underwater imaging plays a crucial role in accurately capturing underwater targets and environmental features. Facing the challenges of complex ocean environments and severe photon attenuation, quantum imaging breaks through the limitations of traditional optical imaging technology by utilizing the characteristics of two-photon entanglement and time-space correlation, thus offering a new perspective on ocean turbulence. To this end, we propose a new underwater entangled-photon quantum imaging system. Specifically, we first construct an entangled photon quantum imaging physical model through ocean long-exposure turbulence and then exploit an entangled light coincidence imaging reconstruction method to image the target object. Furthermore, in response to the problem that ocean environment has a great impact on photons, we develop a photon capture probability method based on entangled photon pairs to reduce the impact of the ocean turbulence noise on imaging and improve the underwater target imaging resolution. We experimentally demonstrate the effectiveness of our method by showing that even in harsh ocean environments, quantum imaging performs superior resolution capabilities over traditional light source imaging techniques.

In this paper, we investigate a cooperative edge caching problem in the fog radio access networks (F-RANs). In order to obtain the globally optimal caching strategy that minimizes the content transmission delay and maximizes communication efficiency, we propose a multi-agent reinforcement learning based cooperative caching policy with low entropy communications. First, we propose a double deep Q network (DDQN) based caching policy by taking into account the non-deterministic polynomial hard (NP-hard) aspect of this cooperative caching optimization problem. Then, we extend the state transition model of Markov Decision Process (MDP) under the single agent system into the Stochastic Game (SG) one under the multi-agent system. By employing the DDQN in each agent, the agents can learn and make the global decision for caching. For utilizing the cooperation resources of fog access points (F-APs), the interaction of information is introduced to exchange the historical cache records of cooperative F-APs. However, the information in the interaction may require lower entropy in the fiber link. Therefore, the information entropy is largely reduced to improve the communication efficiency by quantifying the information. Finally, due to the non-computable gradient of information entropy, we apply a pseudo gradient descent method to approximate the gradient descent in the local model. Simulation results show that our policy achieves better performance in terms of reducing the transmission delay and improving the cooperation among F-APs compared to the benchmark policies. Additionally, it is demonstrated that the proposed policy improves communication efficiency without compromising the performance of cooperative caching.

Mega-satellite constellations have the potential to leverage inter-satellite links to deliver low-latency end-to-end communication services globally, thereby extending connectivity to underserved regions. However, harsh space environments make satellites vulnerable to failures, leading to node removals that disrupt inter-satellite networking. With the high risk of satellite node failures, understanding their impact on end-to-end services is essential. This study investigates the importance of individual nodes on inter-satellite networking and the resilience of mega satellite constellations against node failures. We represent the mega-satellite constellation as discrete temporal graphs and model node failure events accordingly. To quantify node importance for targeted services over time, we propose a service-aware temporal betweenness metric. Leveraging this metric, we develop an analytical framework to identify critical nodes and assess the impact of node failures. The framework takes node failure events as input and efficiently evaluates their impacts across current and subsequent time windows. Simulations on the Starlink constellation setting reveal that satellite networks inherently exhibit resilience to node failures, as their dynamic topology partially restore connectivity and mitigate the long-term impact. Furthermore, we find that the integration of rerouting mechanisms is crucial for unleashing the full resilience potential to ensure rapid recovery of inter-satellite networking.

Integrated sensing and communication (ISAC) can ensure the secure transmission through sensing the eavesdroppers. However, the information obtained by a single base station (BS) is difficult to accurately track the moving eavesdroppers. In this paper, we investigate the sensing-assisted secure communication, where multiple BSs cooperatively sense an unmanned aerial vehicle (UAV) target, also regarded as an aerial eavesdropper. We propose a two-stage scheme to ensure the secure transmission. In the first stage, we estimate the current location and velocity of the UAV through fusing the sensing information from these BSs, to further predict the location in the next time slot. Meanwhile, the prediction variance is derived to bound the errors. In the second stage, we tackle the robust optimization with the prediction errors. Considering the tradeoff between the security and sensing performance, the weighted sum of secrecy rate and radar mutual information rate is maximized via jointly designing the user scheduling and beamforming, which is non-convex. Thus, we decompose it into two subproblems, where the scheduling is obtained via the branch and bound algorithm and the beamforming vectors are optimized by the successive convex approximation. In the end, we design a robust algorithm to address the original problem. Simulation results are shown to prove the efficiency of the proposed scheme.

The metaverse services are promising to embrace multi-sensory experiences of human beings, which mainly include audio-visual and tactile senses. From the perspective of wireless transmission, tactile transmission requires ultra-reliable low-latency communications, while audio-visual transmission requires enhanced mobile broadband communications. Besides, the audio-visual segment can be divided into several correlated data packets, any loss of packets would result in failed decoding at users, thus degrading users’ immersive experiences. In multi-user wireless metaverse systems, the heterogeneous transmission characteristics of multi-modal streams and integrity requirements of audio-visual stream transmission pose a great challenge to the limited wireless resource scheduling. To this end, we design a multi-user resource schedule scheme for multi-modal stream transmission by jointly considering the integrity of audio-visual stream transmission and the puncturing-based tactile stream transmission. We model the multi-modal perception utility function based on the multi-attribute utility theory and wireless transmission performance of multi-modal streams. Then, we formulate the average multi-modal perception utility maximization problem, and we adopt the Lyapunov theory to decompose the original maximization problem. Furthermore, we integrate the matching-based two-timescale spectrum resource allocation algorithm and alternating direction method of multipliers-based power allocation algorithm to obtain the optimal spectrum and power allocation strategies. Simulation results show that, compared with the resource allocation scheme without considering the transmission integrity, the average multi-modal perception utility of the proposed scheme is maximumly improved by 25%.

Holographic metasurface antenna (HMA) has been envisioned as a new antenna paradigm anticipated to realize massive multiple-input multiple-output (MIMO) capability with greatly reduced hardware cost and power consumption. In this paper, we develop a framework for the energy efficiency (EE) optimization in the HMA-assisted uplink (UL) multiuser MIMO (MU-MIMO) system. We consider two types of power constraints, namely, the sum power and box eigenvalue constraints (SPBECs) and the multiple weighted power constraints (MWPCs). In this framework, we firstly formulate a general EE maximization problem subject to SPBECs and propose a novel EE-oriented water-filling algorithm by jointly exploring the quasi-concave property of the EE function and introducing an actual power consumption factor. Based on this, we then develop a low-complexity two-stage algorithm to separately optimize the HMA weighting matrix and the transmit covariance matrix. Specifically, in the first stage, two different algorithms, i.e., the channel alignment based algorithm and the weighted minimum mean square error (WMMSE) based algorithm, are proposed to optimize the HMA weighting matrix. In the second stage, we apply the proposed novel EE-oriented water-filling algorithm to optimize the transmit covariance matrix by respectively introducing per-user and all-user power consumption factors. Moreover, this two-stage algorithm is applicable to the EE optimization under MWPCs by leveraging duality theory to integrate multiple power constraints into a single one. Finally, numerical simulations validate that the proposed algorithms can achieve comparable EE performance to traditional benchmark schemes with significantly reduced computational complexities.

Over-the-air computation (AirComp) is a promising technique that addresses big data collection and fast wireless data aggregation. However, in a network where wireless communication and AirComp coexist, mutual interference becomes a critical challenge. In this paper, we propose to employ an unmanned aerial vehicle (UAV) to enable integrated communication and AirComp, where we capitalize on UAV mobility with alleviated interference for performance enhancement. Particularly, we aim to maximize the sum of user transmission rate with the guaranteed AirComp accuracy requirement, where we jointly optimize the transmission strategy, signal normalizing factor, scheduling strategy, and UAV trajectory. We decouple the formulated problem into two layers where the outer layer is for UAV trajectory and scheduling, and the inner layer is for transmission and computation. Then, we solve the inner layer problem through alternating optimization, and the outer layer is solved through soft actor–critic-based deep reinforcement learning. Simulation results show the convergence of the proposed learning process and also demonstrate the performance superiority of our proposal as compared with the baselines in various situations.

In this paper, we analyze the covert UAV-to-UAV (U2U) communication with the ground warden under a Poisson field of ground interferers and the blockage effect of air-to-ground propagations. With the aid of stochastic geometry, we derive the average covert probability and connection outage probability to quantify the covert communication performance for the scenarios with and without interference. By comparing the two scenarios, the introduction of interference increases the minimum average covert probability. Increasing both the density and transmission power of interferers can improve the average covert probability. However, the improvement of covertness is achieved by increasing the connection outage probability. To capture the competing requirements of covertness and reliability, we analyze the effective covert communication rate defined as the product of the average covert probability, connection success probability, and data transmission rate. The UAV transceiver can also flexibly raise its flight altitude to improve effective covert communication rate. Moreover, our results reveal that covert U2U communication performs better in high blockage environments such as dense urban. In summary, this study provides theoretical guidance for designing covert U2U communication systems.

Large language models (LLMs) have shown great promise in many domains, yet their potential to transform wireless communications, where the escalating complexity of the network outpaces traditional model-based methods, remains largely untapped. Addressing this gap is critical for the next generation of intelligent and adaptive 6G systems. In this work, we develop a specialized dataset aimed at enhancing the evaluation and fine-tuning of LLMs specifically for wireless communication applications. The dataset includes a diverse set of multi-hop questions, including true/false and multiple-choice types, spanning varying difficulty levels from easy to hard. By utilizing advanced language models for entity extraction and question generation, rigorous data curation processes are employed to maintain high quality and relevance. Additionally, we introduce a Pointwise V-Information (PVI) based fine-tuning method, providing a detailed theoretical analysis and justification for its use in quantifying the information content of training data with 2.24% and 1.31% performance boost for different models compared to baselines, respectively. To demonstrate the effectiveness of the fine-tuned models with the proposed methodologies on practical tasks, we also consider different tasks, including summarizing optimization problems from technical papers and solving the mathematical problems related to non-orthogonal multiple access (NOMA), which are generated by using the proposed multi-agent framework. Simulation results show significant performance gain in summarization tasks with 20.9% in the ROUGE-L metrics. We also study the scaling laws of fine-tuning LLMs and the challenges LLMs face in the field of wireless communications, offering insights into their adaptation to wireless communication tasks. This dataset and fine-tuning methodology aim to enhance the training and evaluation of LLMs, contributing to advancements in LLMs for wireless communication research and applications.

In this paper, we investigate the joint data relay communication and semantic communication in an unmaned aerial vehicle (UAV)-based Metaverse system. Therein, UAVs as relays forward data from ground users to ground data collectors (GDCs). Meanwhile, they capture images of area of interests, and the images can be used to update digital twin (DTs) for Metaverse platforms. As the UAVs and their GDCs may belong to different platforms, they may use the same spectrum at the same time that cause interference to each other. A third party, i.e., a network service provider (NSP), is involved to provide licensed channels in terms of transmission periods to the UAVs. We design auction schemes as incentive mechanisms for trading the transmission periods between the UAVs and the NSP. With a single transmission period, we design a learning auction with neural networks constructed from the Myerson theorem that maximizes the NSP’s revenue while ensuring important economic properties. With multiple transmission periods, we develop a nearly-optimal auction scheme by using attention mechanisms. A semantic communication technique is implemented at each UAV to reduce the size of the original images and cost for using the licensed channels. Extensive experiments shows that the learning auction driven from the Myerson theorem outperform the baseline scheme in terms of NSP’s revenue and truthfulness, while the revenue obtained by the attention-based auction is much higher than the existing learning auction.

The communication network in a tunnel construction site facilitates real-time data exchange, and serves as a backbone for successfully executing construction projects. However, the long and closed spaces, irregular surfaces, and variable topology as tunnel excavation impose rigorous limitations on signal propagation, communication quality and coverage. To alleviate the realistic issues, we introduce a holistic three-phase cooperative relay scheme based on 5G New Radio (NR) vehicle-to-everything (V2X) architecture, which can extend the communication range and enhance network throughput. We theoretically derive the outage probability of the entire cooperative relaying process from source to destination, and quantify the impact of relaying on construction workflow with relay cost. To minimize the outage probability and relay cost, we formulate a cooperative relay strategies optimization problem and transform the solving procedure into a Markov decision process (MDP). We design a hybrid hierarchical proximal policy optimization (HH-PPO) reinforcement learning method to solve the MDP, which consists of two discrete actor networks, two continuous actor networks, and two critic networks. The hybrid structure enables HH-PPO to tackle the mixed action space, and the hierarchical structure enables adaptive and contextual actions generation by integrating the discrete network outputs into the continuous actor network. Simulation results validate the effectiveness of the HH-PPO algorithm with faster convergence speed, and show superior performance in terms of lower, stable outage probability and relay cost satisfaction compared with another benchmark.

Integrating feeder- and user-links in multi-beam satellite communications significantly enhances system flexibility but requires effective resource allocation to fully realize its potential. Multi-agent deep reinforcement learning (MADRL) has emerged as a scalable solution for beam hopping, by allowing each agent to optimize the transmission parameters for one beam. However, integrating feeder- and user-links introduces complicated dependencies, including resource competition between feeder- and user-links and data-flow coupling between uplinks and downlinks, dramatically deteriorating agent cooperation. To approach the performance limit, this paper introduces a dependency-elimination MADRL framework incorporating model decomposition, link decoupling, and novel agent-level collaboration mechanisms to allocate beams, power, and bandwidth with reduced complexity. Specifically, to facilitate beam-level agent reuse for complexity reduction under the heterogeneity of feeder- and user-links, characterized by data-flow aggregation and division, we decouple bandwidth allocation from the learning model. The uplink-downlink dependencies in the bandwidth allocation is then resolved using a generalized water-filling strategy based on the performance upper bounds. Furthermore, we improve agent cooperation efficiency through state and reward decomposition and a novel non-cooperation penalty. Evaluations show that our method improves the system performance by up to 57.7% compared to sota MADRL methods while reducing training complexity by more than 50%.

In this paper, we propose a multi-unmanned aerial vehicle (UAV)-assisted integrated sensing, communication, and computation network. Specifically, the treble-functional UAVs are capable of offering communication and edge computing services to mobile users (MUs) in proximity, alongside their target sensing capabilities by using multi-input multi-output arrays. For the purpose of enhance the computation efficiency, we consider task compression, where each MU can partially compress their offloaded data prior to transmission to trim its size. The objective is to minimize the weighted energy consumption by jointly optimizing the transmit beamforming, the UAVs’ trajectories, the compression and offloading partition, the computation resource allocation, while fulfilling the causal-effect correlation between communication and computation as well as adhering to the constraints on sensing quality. To tackle it, we first reformulate the original problem as a multi-agent Markov decision process (MDP), which involves heterogeneous agents to decompose the large state spaces and action spaces of MDP. Then, we propose a multi-agent proximal policy optimization algorithm with attention mechanism to handle the decision-making problem. Simulation results validate the significant effectiveness of the proposed method in reducing energy consumption. Moreover, it demonstrates superior performance compared to the baselines in relation to resource utilization and convergence speed.

With the diversification of wireless applications, the traffic patterns in the evolving wireless networks are becoming more dynamic and heterogeneous. Although numerous methods have been developed for spatio-temporal analysis, the impact of traffic patterns on spatial capacity has yet to be fully addressed. To this end, this paper studies the spatial outage capacity (SOC) in Poisson networks with Bernoulli traffic, which answers the question: “What is the maximum density of concurrently active links that satisfy a certain outage constraint?” We perform the analysis by integrating stochastic geometry with queueing theory and derive the meta distribution (MD) of signal-to-interference ratio (SIR). Unlike the conventional approaches that approximate the MDs by beta distributions, we consider the spatio-temporal correlations of the dominant interference exactly while treating the remaining interference in an average sense. Our analysis maintains tractability and achieves a highly accurate characterization of the SIR, especially for dense networks in the high-reliability regime that is particularly significant for network design. Moreover, we prove that the SOC in the high-reliability regime is achieved when all transmitters are always active. Simulations validate the accuracy of the theoretical results and show that the packet arrival rate has a marginal effect on the SOC as well as the corresponding SIR MD. We also show that the optimal density that maximizes the SOC is approximately inversely proportional to the packet arrival rate.

We investigate a heterogeneous network (HetNet) including sub-6GHz base stations (BSs), mmWave BSs, and THz BSs to support enhanced mobile broadband (eMBB) users and ultra-reliable low-latency communication (URLLC) users. We particularly investigate a user-centric network in which the users locally and dynamically select and switch among BSs over time to achieve their highest utility. Two types of users have different Quality of Service (QoS) requirements. Thus, we design two types of utility functions specifically for the eMBB users and URLLC users. Then, to model the dynamic selection behavior of the users, we propose to use a fractional game with the power-law memory. The fractional game allows the eMBB users and the URLLC users to incorporate their past strategies into their current selection, thus improving their utility. Furthermore, we consider the case that the BSs communicate the system state with each other, and we model the network selection of the users as a multi-agent problem. Then, we propose to use a multi-agent deep reinforcement learning (MADRL) algorithm that enables the URLLC users and eMBB users to make their network selection decision online to achieve their long-term utility. Various simulation results are provided to demonstrate the scalability and effectiveness of the proposed approaches. Particularly, compared with the classical game, the fractional game is able to achieve a higher utility but incurs a higher network adaptation cost. Moreover, the different types of URLLC users (in terms of latency and reliability requirements) and the number of URLLC users in the network significantly affect the total utility and the network selection strategies of the eMBB users. Importantly, given the full observations, the MADRL outperforms both classical and fractional games in terms of total network utility.

Wireless networked control systems (WNCSs) have emerged as a new paradigm in industrial Internet of Things (IIoT), where base station (BS) transmits control commands generated by the remote controller to actuators of multiple control subsystems through shared wireless channels. This paper investigates a novel rate splitting multiple access (RSMA) enabled ultra-reliable and low-latency (URLLC) transmission design for industrial control applications in WNCSs, where control commands are splitted and transmitted with finite blocklength regime. This design aims to maximize the system sum rate (SR) by optimizing beamforming at BS, rate control for each control subsystem, and user pairing between control subsystems and subcarriers, while ensuring the control stability requirements for all control subsystems. We first derive the control convergence constraint into a communication reliability constraint expressed in terms of outage probability. Then we propose a nested iterative algorithm adopting alternating optimization (AO). During the inner iteration, we propose a resource allocation method leveraging successive convex approximation (SCA) to jointly optimize beamforming and rate control, while during the outer iteration, a hypergraph game-theoretic based matching method is provided to obtain the optimal pairing result between control subsystems and subcarriers. Simulation results demonstrate that the proposed transmission design outperforms existing schemes in terms of communication rate and control cost.

Recently, semantic communication (SemCom) has shown great potential in significant resource savings and efficient information exchanges, thus naturally introducing a novel and practical cellular network paradigm where two modes of SemCom and conventional bit communication (BitCom) coexist. Nevertheless, the involved wireless resource management becomes rather complicated and challenging, given the unique background knowledge matching and time-consuming semantic coding requirements in SemCom. To this end, this paper jointly investigates user association (UA), mode selection (MS), and bandwidth allocation (BA) problems in a hybrid semantic/bit communication network (HSB-Net). Concretely, we first identify a unified performance metric of message throughput for both SemCom and BitCom links. Next, we specially develop a knowledge matching-aware two-stage tandem packet queuing model and theoretically derive the average packet loss ratio and queuing latency. Combined with practical constraints, we then formulate a joint optimization problem for UA, MS, and BA to maximize the overall message throughput of HSB-Net. Afterward, we propose an optimal resource management strategy by utilizing a Lagrange primal-dual transformation method and a preference list-based heuristic algorithm with polynomial-time complexity. Numerical results not only demonstrate the accuracy of our analytical queuing model, but also validate the performance superiority of our proposed strategy compared with different benchmarks.

Although integrated sensing and communication (ISAC) has an advantage of mutual gain of its dual functions, it is susceptible to be eavesdropped by mobile targets due to the broadcast nature of wireless channels. In this paper, we propose a secure predictive beamforming scheme against a mobile eavesdropping target for ISAC, where the intelligent reflecting surface (IRS) is utilized to assist the sensing and secure transmission. To tackle the mobility of eavesdropping target, we first develop a secure predictive beamforming protocol and formulate a sum secrecy rate maximization problem. However, due to the non-convex objective function and the outdated channel state information (CSI), it is difficult to solve the problem directly. Thus, we develop a deep learning based predictive beamforming scheme, which incorporates the parallel convolutional neural network, the long short-term memory modules and the attention mechanism to learn the features from the historical CSI. It can directly design the beamformings for the next time slot with low computational complexity and bypass the need of CSI prediction. Simulation results show that the proposed scheme can significantly enhance the security of ISAC with low overhead.

This paper investigates an unmanned aerial vehicle (UAV)-base station (BS) integrated network, where a UAV transmits downlink secrecy data to multiple ground cognitive users while a ground BS utilizes jamming beamforming to help the UAV counter the eavesdropping attack of a ground eavesdropper. In particular, we consider the imperfect eavesdropping and jamming channel state information (CSI) related to the eavesdropper. To maximize the minimum sum secrecy rate of the cognitive users, a robust secure transmission scheme is proposed. The UAV trajectory, UAV transmit power, BS beamforming, and user scheduling are jointly optimized with the constraints of the communication quality of the primary users served by the BS and the UAV available propulsion energy. We formulate a non-convex optimization problem which is challenging to be solved mathematically, and we utilize an alternating optimization technique to divide the original problem into three sub-problems, i.e., UAV trajectory sub-problem, transmit power sub-problem, and user scheduling sub-problem. Besides, they can be solved by the successive convex approximation, semi-definite relaxation and S-procedure, and bivariate relaxation methods, respectively. Moreover, we explore the impact of different parameters of the proposed transmission scheme on the minimum sum secrecy rate of the cognitive users, and verify the superiority of the proposed robust secure transmission scheme design.

We propose a robust transceiver design for a covert integrated sensing and communications (ISAC) system with imperfect channel state information (CSI). Considering both bounded and probabilistic CSI error models, we formulate worst-case and outage-constrained robust optimization problems of joint transceiver beamforming and radar waveform design to balance the radar performance of multiple targets while ensuring the communications performance and covertness of the system. The optimization problems are challenging due to the non-convexity arising from the semi-infinite constraints (SICs) and the coupled transceiver variables. In an effort to tackle the former difficulty, S-procedure and Bernstein-type inequality are introduced for converting the SICs into finite convex linear matrix inequalities (LMIs) and second-order cone constraints. A robust alternating optimization framework referred to alternating double-checking is developed for decoupling the transceiver design problem into feasibility-checking transmitter- and receiver-side subproblems, transforming the rank-one constraints into a set of LMIs, and verifying the feasibility of beamforming by invoking the matrix-lifting scheme. Numerical results are provided to demonstrate the effectiveness and robustness of the proposed algorithm in improving the performance of covert ISAC systems.

Cell-free (CF) massive multiple-input multiple-output (MIMO) provides a ubiquitous coverage to user equipments (UEs) but it is also susceptible to interference. Rate-splitting (RS) effectively extracts data by decoding interference, yet its effectiveness is limited by the weakest UE. In this paper, we investigate an RS-based CF massive MIMO system, which combines strengths and mitigates weaknesses of both approaches. Considering imperfect channel state information (CSI) resulting from both pilot contamination and noise, we derive a closed-form expression for the sum spectral efficiency (SE) of the RS-based CF massive MIMO system under a spatially correlated Rician channel. Moreover, we propose low-complexity heuristic algorithms based on statistical CSI for power-splitting of common messages and power-control of private messages, and genetic algorithm is adopted as a solution for upper bound performance. Furthermore, we formulate a joint optimization problem, aiming to maximize the sum SE of the RS-based CF massive MIMO system by optimizing the power-splitting factor and power-control coefficient. Importantly, we improve a generative AI (GAI) algorithm to address this complex and non-convexity problem by using a diffusion model to obtain solutions. Simulation results demonstrate its effectiveness and practicality in mitigating interference, especially in dynamic environments.

In this paper, we investigate hybrid passive and active intelligent reflecting surface (IRS)-assisted secure non-orthogonal multiple access (NOMA) networks. Multiple users concurrently transmit sensitive data to an access point (AP) in the presence of an eavesdropper (Eve). The hybrid IRS is employed to enhance the NOMA users’ sum rates while simultaneously performing jamming beamforming against the Eve by optimizing the communication channels of NOMA users and injecting controllable noise into the Eve’s channel. We formulate a sum secrecy rate maximization problem by jointly optimizing the users’ scheduling policy, the hybrid IRS’s working mode and beamforming, and the AP’s receiving beamforming. To address combinatorial user scheduling and high-dimensional beamforming design, we develop a dual-cycling deep reinforcement learning (DRL) framework. We first determine the NOMA users’ scheduling strategy and the hybrid IRS’s working mode using a proximal policy optimization (PPO)-based learning algorithm. Then, we optimize the AP’s receiving beamforming and hybrid IRS’s beamforming strategies using an alternating optimization (AO) algorithm. The joint beamforming optimization can significantly enhance the DRL’s learning efficiency by limiting its action space. Moreover, we propose a lightweight two-phase algorithm with approximation techniques to reduce computational complexity by eliminating double-nested loops in AO, while maintaining secrecy performance close to optimum. Numerical results demonstrate that the proposed dual-cycling DRL scheme achieves 54.85% gains in the secrecy rate compared to traditional DRL schemes.

Unmanned Aerial Vehicles-based Multiple Targets Tracking (UAV-MTT) has been mainstream in serving mission-critical scenarios for public safety, such as hit-and-run tracking and border patrol. Nonetheless, it is challenging to implement high-efficiency UAV topology control due to the variable moving speeds of targets and the limited sensing and communication resources of UAVs. To address the problem, we propose a terminal-edge cooperative Digital Twin (DT) framework for real-time and accurate MTT. Based on the DT technology, we achieve joint optimization of local and global UAV topologies to track targets with diverse speeds. Explicitly, we construct time-spatial DT models based on temporal and spatial information of targets and UAVs. The DT models can instruct UAVs to dynamically adjust position relations among one-hop neighbors for local topology optimization using our proposed Time Spatial Graph Learning based DT (TSGL-DT) algorithm. UAVs can use the optimization results to invite feasible neighbors to track low-speed moving targets. Our DT models can also allocate feasible UAVs to connect suitable local topologies for global topology optimization. It can achieve cooperative MTT to track high-speed moving targets. The experiment results demonstrate that our solution reduces the MTT latency by 41.2% while improving the successful tracking ratio delivery ratio by 15.6% on average compared to state-of-the-art benchmarks.

In advanced vehicular networks, Roadside Unit (RSU)-based amplify-and-forward (AF) relay and passive Reconfigurable Intelligent Surface (RIS) are two potential helpers to enhance the vehicle-to-vehicle (V2V) communications when the direct link experiences poor quality. This paper presents a comprehensive comparison of the two enhancement modes from the outage performance perspective. In the presence of both direct link and enhanced link, the analytical expressions of the outage probability (OP) for the V2V communication under the two enhancement modes are derived respectively. Moreover, considering the co-channel interference caused by relay/RIS, the OP of the neighbouring vehicle-to-infrastructure (V2I) communication is also derived. Additional analysis compares the diversity order and the strength of interference created by the V2V communication under the two enhancement modes. Further discussions are presented on the effect of the channel estimation error and phase quantization error under the RIS mode. Finally, the pros and cons of the two enhancement modes are demonstrated by both the analytical and numerical results.

Semantic communication has recently garnered substantial attention due to its potential to alleviate bandwidth constraints and improve network capacity. Nonetheless, existing studies primarily concentrate on network architecture and overlook the communication performance analysis. Therefore, this paper seeks to derive semantic-oriented error probability. Specifically, we develop a novel text semantic communication framework that comprises distinct semantic and physical layers. In the semantic layer, we employ latent Dirichlet allocation (LDA) to extract text topics and evaluate the topic distribution. Given an expected transmission accuracy, we propose a dichotomy to determine the minimal number of topics. These acquired topics, along with their respective distributions, are defined as the text semantic features. In the physical layer, the semantic features are encoded into a binary sequence and modulated with conventional methods. The relationship between the semantic and physical layers is uncover by associating coding of the semantic features with the symbol error probability (SEP). Considering a scenario wherein base stations (BSs) following a specific Poisson point process (PPP), we derive the approximate SEP and semantic inference error probability (SIEP) for multiple coding strategies. Simulation results show that the proposed text semantic communication network enables effective text transmission and the derived error probability accurately reflect the performance of an actual communication system.

As decentralized storage becomes more prevalent, ensuring data integrity within these systems has gained increasing importance. However, the introduction of a centralized and trustedCloud Combiner(CO) to manage auditing across distributedCloud Servers(CSs) presents several challenges, which not only increases communication costs with independent CSs but also diminishes the credibility of the auditing results. Additionally, traditional approaches often require either certificate and key management or the establishment of secure transmission channels, which incur substantial overhead. Furthermore, the computational cost for index generation to support searchable auditing is often high. To address these challenges, we propose a collaborative and searchable integrity auditing scheme for multi-replica data that eliminates the need for a CO. Specifically, we design a certificate-based authenticator for multi-copy data blocks, which simplifies certificate and key management while removing the need for secure channels. To enable efficient searchable auditing, we introduce a novel index tag that matches authenticators, thereby reducing the computational overhead. Moreover, we leverage blockchain technology to enhance the credibility of the auditing process and ensure the integrity of the search results. Both security and performance analyses demonstrate that the proposed scheme is secure and efficient.

Federated learning (FL) contributes to data privacy by not disclosing raw data, but encounters challenges of privacy leakage from local gradient uploading. This paper introduces a novel over-the-air computation (AirComp)-based FL system that balances privacy and accuracy by leveraging the waveform superposition and channel propagation characteristics of AirComp. Specifically, we derive the privacy leakage metric to explicitly account for the effects of waveform aggregation and communication noise. We analyze the convergence upper bound to capture model update errors stemming from artificial and communication noise. We formulate a new joint privacy-accuracy optimization problem by incorporating privacy leakage in the model training objective, guiding the learning process towards enhanced privacy protection. We then employ convex optimization techniques to derive the optimal power scaling and artificial noise intensity. Simulations demonstrate up to 80% reduction in privacy leakage compared to baselines under stringent privacy constraints, while maintaining competitive learning performance. Our method exhibits enhanced robustness under low signal-to-noise ratios, achieving 40% lower privacy leakage under equivalent privacy budgets.

Federated Learning (FL) allows multiple data owners to jointly train machine learning models by sharing local models instead of raw private data, alleviating data privacy concerns. However, as the local computation of data owners is unpredictable, it increases its vulnerability to Byzantine attacks, where compromised data owners submit abnormal local models that can severely degrade global model accuracy. Existing Byzantine-robust FL methods depend on a semi-honest server executing predefined Byzantine-robust aggregation rules (ByRules) to filter out abnormal local models, but these methods fail when the server is compromised. Although recent serverless Byzantine-robust FL approaches mitigate the risk of a compromised server, they suffer from challenges in achieving consensus on ByRules and impose a heavy burden on privacy protection. In this paper, we propose ROBY, a novel serverless FL framework that extends existing ByRules to a decentralized setting, effectively defending against Byzantine attacks and ensuring privacy protection for local models. ROBY introduces a shared, dynamically updated consensus dataset that serves as a reliable benchmark for applying ByRules and enabling efficient consensus on ByRules among decentralized data owners. Moreover, we design a dual-layer privacy shielding strategy in ROBY to protect local model privacy without sacrificing global model accuracy or incurring extra computational and communication overhead. Extensive evaluations demonstrate that ROBY substantially enhances both Byzantine robustness and privacy protection compared to server-based FL methods.

Federated Learning (FL) has emerged as a promising distributed machine learning paradigm that allows clients to jointly train a global model without sharing their raw training datasets. However, FL is vulnerable to backdoor attacks, where malicious clients inject specific backdoors into their local models to manipulate the global model’s outputs. Recent studies widely applied gradient compression to construct efficient and robust FL systems against backdoor attacks, but we argue that gradient compression cannot be seen as a reliable defense strategy against backdoor attacks. In this work, we systematically evaluate the effectiveness of gradient compression against backdoor attacks. The experimental results indicate that, in addition to the effectiveness of SignSGD in preventing backdoor injection without significantly reducing the accuracy of the global model, most gradient compression methods do not provide effective defenses against backdoor attacks. Furthermore, we develop a novel adaptive backdoor attack, named FinBack, that can effectively infiltrate the gradient compressor SignSGD and implant backdoors in FL, by inducing small weight changes on specific neurons that do not conflict with benign clients while avoiding counteraction by benign clients and perturbation triggers thereby ensuring the effectiveness and persistence of backdoors. FinBack encompasses two attack modes: FinBack with the server collusion and FinBackR without the server collusion. Extensive experiments demonstrate the effectiveness and persistence of the proposed attacks, which increases the Attack Success Rate (ASR) from 10% to over 90% in SignSGD, even with 1% of malicious clients.

Integrated sensing and communications (ISAC) is one of the crucial technologies for 6G, and channel state information (CSI) based sensing serves as an essential part of ISAC. However, current research on ISAC focuses mainly on improving sensing performance, overlooking security issues, particularly the unauthorized sensing of users. Hence, this paper proposes a diffusion model based secure sensing system (DFSS). Specifically, we first propose a discrete conditional diffusion model to generate graphs with nodes and edges, which guides the ISAC system to appropriately activate wireless links and nodes, ensuring the sensing performance while minimizing the operation cost. Using the activated links and nodes, DFSS then employs the continuous conditional diffusion model to generate safeguarding signals, which are next modulated onto the pilot at the transmitter to mask fluctuations caused by user activities. As such, only authorized ISAC devices with the safeguarding signals can extract the true CSI for sensing, while unauthorized devices are unable to perform the effective sensing. Experiment results demonstrate that DFSS can reduce the activity recognition accuracy of the unauthorized devices by approximately 70%, effectively shield the user from the illegitimate surveillance.

Digital identity is fundamental for accessing mobile applications and managing user attributes. However, existing centralized identity management solutions rely on third-party operators, posing privacy risks and limiting user control. The decentralized solutions seek to address the issues but often fall short in privacy preservation, efficiency, and cross-application compatibility. In this paper, we propose PPUgIM, a user-governed identity management scheme with universally composable security, emphasizing privacy and data sovereignty in distributed mobile applications. PPUgIM introduces a DID-like account equipped with multi-attribute credentials, enabling users to autonomously manage and selectively disclose various identities without revealing sensitive information. An enhanced authenticated data structure is designed based on vector commitments, supporting short and constant-size proofs for efficient batch authentication of attribute credentials. Furthermore, a formal security analysis of PPUgIM is conducted, and a prototype implementation is developed for performance evaluation. Results show that credential generation takes 500 ms, verification 110 ms, with a constant size proof of 0.15 KB. Proof overhead for identities is reduced by 38.1% compared with existing schemes, demonstrating PPUgIM’s practicality in real-world distributed mobile applications.

With the increasing demands of the Industrial Internet of Things (IIoT), highly dynamic multi-unmanned aerial vehicle (UAV) networks are becoming indispensable to IIoT due to their flexibility, cost-effectiveness, robust safety measures, and real-time data collection capabilities. Accurate time synchronization is crucial for coordinated missions of multi-UAV networks, yet the time-varying nature of clock parameters and the rapid movements of UAVs pose significant challenges to achieving precise synchronization. This article introduces new state and observation models for clock and velocity parameters and proposes a Doppler and timestamp-based distributed algorithm for tracking clock parameters using the Kalman filter. To evaluate the performance of the proposed algorithm, we derive the Bayesian Cramér–Rao lower bound and conduct numerical simulations. The results of the simulations demonstrate that our algorithm surpasses existing methods in terms of accuracy in tracking clock parameters.

The frequency-modulated continuous wave (FMCW) radar has received much attention in the field of noncontact vital signs monitoring. However, since vital signs are usually very weak, it can be easily buried by interference and noise, especially for the heartbeat signal. To tackle this challenge, this article proposes a novel systematic vital signs detection framework using the multiple-input multiple-output FMCW radar. First, the signal noise ratio of the vital signs signal is enhanced by combining the phase signals of multiple channels using the maximum ratio combining method. Then, to suppress noise and interference, we construct the vital signs signal with singular spectral analysis and propose a correlation-based selection criterion to select potential intrinsic mode functions of the respiration and heartbeat signals. Finally, a fast independent component analysis is applied to extract the respiration signal, and the second-order derivative based fast independent component analysis in conjunction with an infinite impulse response notch filter is further developed to extract the heartbeat signal. Simulations and experimental results validate the effectiveness of the proposed framework.

Vehicle platooning has emerged as a promising solution for efficient traffic management. Multiple platoons traveling in a cooperative way can alleviate congestion and enhance driving safety by information sharing and consensus. To address the data security and privacy concerns, blockchain could be applied to enable secure data sharing and consensus across multiple platoons. However, existing performance of blockchain is insufficient to ensure reliable and efficient data consensus among multiple platoons. First, the hierarchical structure of platoons with different roles of vehicles complicates the trust establishment between platoons, making it challenging to evaluate their trustworthiness and ensure consensus reliability. Additionally, data sharing in vehicle platooning networks demands timely information and efficient consensus-building. To tackle above challenges, we design a role-adaptive trust model for trust evaluation of platoons in consideration of different roles of vehicles within a platoon. Based on the proposed model, we formulate a blockchain consensus optimization problem to facilitate both reliability and efficiency of data consensus among multiple platoons. Leveraging Generative Artificial Intelligence (GenAI) techniques, we then propose the Diffusion Enhanced Soft Actor-Critic (DESAC) by integrating the diffusion model and SAC, to further improve the performance of blockchain consensus. Experiment results demonstrate the effectiveness and efficiency of the proposed consensus optimization approach.

As an emerging technology, Digital Twin (DT) can provide a virtual representation of transportation infrastructures to achieve efficient and precise management of Intelligent Transportation Systems (ITS). However, a mixed traffic scenario of coexisting intelligent connected vehicles (ICVs) and non-intelligent connected vehicles (N-ICVs) increases challenges for digital ITS. N-ICVs are unable to generate and update their DT models independently due to constrained communication and computing capabilities. It is crucial to achieve real-time DT model update and migration of N-ICVs. In this paper, we propose a cooperative perception aided DT model update and migration approach, which dispatches ICVs to cooperatively sense and transmit information of nearby N-ICVs to assist in generating N-ICVs’ DT models. In particular, with the objective of minimizing the average maximum weighted age of information (AMWAoI), we jointly optimize the cooperative ICV selection as well as the bandwidth and computation allocations while guaranteeing the perception performance. We then propose a sensing data weighted size maximization matching algorithm to achieve an optimal ICV selection strategy, and the bandwidth and computation allocations are optimized by the gradient descent algorithm. Considering the dynamic nature of vehicular networks, a deep reinforcement learning-based access selection and DT model migration algorithm is further proposed to achieve continuous service provisioning. Simulation results demonstrate that the proposed algorithm achieves the lowest AMWAoI while meeting the perception performance requirement.

Traffic speed prediction is significant for intelligent navigation and congestion alleviation. However, making accurate predictions is challenging due to three factors: 1) traffic diffusion, i.e., the spatial and temporal causality existing between the traffic conditions of multiple neighboring roads, 2) the poor interpretability of traffic data with complicated spatio-temporal correlations, and 3) the latent pattern of traffic speed fluctuations over time, such as morning and evening rush. Jointly considering these factors, in this paper, we present a novel architecture for traffic speed prediction, calledInterpretable Causal Spatio-Temporal Diffusion Network(ICST-DNET). Specifically, ICST-DNET consists of three parts, namely the Spatio-Temporal Causality Learning (STCL), Causal Graph Generation (CGG), and Speed Fluctuation Pattern Recognition (SFPR) modules. First, to model the traffic diffusion within road networks, an STCL module is proposed to capture both the temporal causality on each individual road and the spatial causality in each road pair. The CGG module is then developed based on STCL to enhance the interpretability of the traffic diffusion procedure from the temporal and spatial perspectives. Specifically, a time causality matrix is generated to explain the temporal causality between each road’s historical and future traffic conditions. For spatial causality, we utilize causal graphs to visualize the diffusion process in road pairs. Finally, to adapt to traffic speed fluctuations in different scenarios, we design a personalized SFPR module to select the historical timesteps with strong influences for learning the pattern of traffic speed fluctuations. Extensive experimental results on two real-world traffic datasets prove that ICST-DNET can outperform all existing baselines, as evidenced by the higher prediction accuracy, ability to explain causality, and adaptability to different scenarios.

Mobile Edge Computing (MEC) reduces the computational burden on terminal devices by shortening the distance between these devices and computing nodes. Integrating Uncrewed Aerial Vehicles (UAVs) with enhanced MEC networks can leverage the high mobility of UAVs to flexibly adjust network topology, further expanding the applicability of MEC. However, in highly dynamic and complex real-world environments, it is crucial to balance task offloading effectiveness with algorithm performance. This paper investigates a multi-UAV communication network equipped with edge computing nodes to assist terminal users in task computation. Our goal is to reduce the task processing delay for users through the joint optimization of discrete computation modes, continuous 3D trajectories, and resource assignment. To address the challenges posed by the mixed action space, we propose a Multi-UAV Edge Computing Resource Scheduling (MUECRS) algorithm, which comprises two key components: 1) trajectory optimization, and 2) computation mode and resource management. Experimental results show that our method effectively plans 3D UAV trajectories and enables rapid user coverage. Compared to state-of-the-art baselines, our approach achieves at least 16.5% reduction in task delay, demonstrating superior adaptability and robustness.

This paper proposes a weight-aware deep reinforcement learning (WADRL) approach designed to address the multiobjective vehicle routing problem with time windows (MOVRPTW), aiming to use a single deep reinforcement learning (DRL) model to solve the entire multiobjective optimization problem. The Non-dominated sorting genetic algorithm-II (NSGA-II) method is then employed to optimize the outcomes produced by the WADRL, thereby mitigating the limitations of both approaches. Firstly, we design an MOVRPTW model to balance the minimization of travel cost and the maximization of customer satisfaction. Subsequently, we present a novel DRL framework that incorporates a transformer-based policy network. This network is composed of an encoder module, a weight embedding module where the weights of the objective functions are incorporated, and a decoder module. NSGA-II is then utilized to optimize the solutions generated by WADRL. Finally, extensive experimental results demonstrate that our method outperforms the existing and traditional methods. Due to the numerous constraints in VRPTW, generating initial solutions of the NSGA-II algorithm can be time-consuming. However, using solutions generated by the WADRL as initial solutions for NSGA-II significantly reduces the time required for generating initial solutions. Meanwhile, the NSGA-II algorithm can enhance the quality of solutions generated by WADRL, resulting in solutions with better scalability. Notably, the weight-aware strategy significantly reduces the training time of DRL while achieving better results, enabling a single DRL model to solve the entire multiobjective optimization problem.

Accurate future traffic flow prediction is essential for decision-making in travel recommendations and route planning, aiming to reduce congestion and enhance traffic safety. Traditional traffic flow prediction models often face limitations in quality and structure, leading to increased training costs and inefficiencies, due to data scarcity and centralized training modes that compromise data privacy. To address these issues, we propose a model called 2MGTCN, which combines Multi-modal Graph Convolutional Networks (GCN) and Temporal Convolutional Networks (TCN) for Cross-city Traffic Flow Prediction (TFP). Our 2MGTCN model utilizes federated transfer learning (FTL) to transfer the model from the source to the target domain, mitigating data scarcity. It also incorporates GCN and TCN to capture both spatial and temporal information, enhancing cross-city adaptability. Additionally, Grey Relation Analysis (GRA) and Dynamic Time Warping (DTW) methods are applied to capture road relationships, and a Federated Parameter Aggregation based on Spatial Similarity (FPASS) algorithm is proposed for ensuring effective parameter aggregation by considering spatial similarity. Simulation results show that our 2MGTCN algorithm outperforms traditional TFP models in both centralized and distributed training modes, ensuring higher accuracy and better privacy protection.

We study decentralized federated learning (DFL) in edge computing networks where edge nodes (ENs) collaboratively train their artificial intelligence (AI) models in a serverless manner without sharing local data. We consider the following critical DFL challenges: i) scarce bandwidth resources of ENs; ii) dynamic, heterogeneous edge environment; iii) incentive provisioning and complex tradeoffs between the DFL performance and training costs. To resolve these challenges, we develop a new model compression method where ENs utilize dynamic, non-identical compression rates to improve the communication efficiency of DFL under time-varying, heterogeneous resource constraints. We show that our method can be formulated as a graphical Markov potential game where ENs act as players deciding on their compression factors and the number of data samples used for model updates. Each EN is incentivized to participate in DFL through rewards based on the EN's contribution to training. We prove that our game has a dominant pure-strategy Nash equilibrium (NE) maximizing its potential function and propose a dynamic distributed compression algorithm in which each EN can find its dominant strategy independently. We show that this algorithm converges to the Pareto-optimal NE, representing the most efficient solution of our game enhancing the DFL performance with minimal costs.

In this paper, we consider a cargo autonomous aerial vehicle (AAV)-aided multi-parcel pick-up and delivery network, where the communication ability of the AAV is provided by the ground base stations (GBSs). For such a system setup, our goal is to optimize the trajectory of the cargo AAV while minimizing the combined impact of total energy consumption and total outage time. Simultaneously, we aim to maximize overall user satisfaction throughout the entire flight duration. More specifically, we propose a pick-up and delivery of AAV (PDU) framework to address this problem and this framework consists of two parts. First, a simulated annealing (SA) algorithm is used to obtain the pick-up and delivery (P&D) order of parcels. On the basis of obtaining the P&D order through SA, we further use deep reinforcement learning (DRL) to optimize the flight trajectory of the AAV to ensure the expected communication quality between the AAV and GBSs. To verify the effectiveness of our proposed algorithms, we design three baseline strategies for comparison, and also investigate the effect of using the PDU framework with different weights. Finally, numerical results show that the performance of PDU strategy is improved by about 5%-30% compared with other strategies in solving the performance tradeoff of AAV energy consumption, communication quality, and user satisfaction.

Authentication is a fundamental requirement and a crucial topic in wireless communications. This paper focuses on improving the security of the prior tag-based Physical-Layer Authentication (PLA) schemes. We propose two phase-tag-based PLA schemes to overcome the limitations of prior tag-based PLA schemes. First, we propose the Phase-Tag-based PLA (PT-PLA) scheme, which superimposes a tag to the phase of the transmitted signal rather than the amplitude. Second, we propose the Adaptive Phase-Tag-based PLA (APT-PLA) scheme, where an appropriate parameter of the PT-PLA scheme is adaptively set for achieving a better trade-off among robustness, security, and compatibility. Rigorous theoretical analyses of the proposed schemes are conducted in high-order modulation systems, such as$M$-PSK and${M}$-QAM systems, with a focus on evaluating their robustness, security, and compatibility. We also discuss advantages and disadvantages of these schemes and offer helpful recommendations according to different scenarios. Furthermore, we implement the proposed schemes and perform extensive simulations to compare their performance comprehensively. Simulation results demonstrate a perfect match with the theoretical results, verifying the superiority of the proposed schemes over the prior schemes.

Vehicle Twins (VTs) as digital representations of vehicles can provide users with immersive experiences in vehicular metaverse applications, e.g., Augmented Reality (AR) navigation and embodied intelligence. VT migration is an effective way that migrates the VT when the locations of physical entities keep changing to maintain seamless immersive VT services. However, an efficient VT migration is challenging due to the rapid movement of vehicles, dynamic workloads of Roadside Units (RSUs), and heterogeneous resources of the RSUs. To achieve efficient migration decisions and a minimum latency for the VT migration, we propose a multi-agent split Deep Reinforcement Learning (DRL) framework combined with spatio-temporal trajectory generation. In this framework, multiple split DRL agents utilize split architecture to efficiently determine VT migration decisions. Furthermore, we propose a spatio-temporal trajectory generation algorithm based on trajectory datasets and road network data to simulate vehicle trajectories, enhancing the generalization of the proposed scheme for managing VT migration in dynamic network environments. Finally, experimental results demonstrate that the proposed scheme not only enhances the Quality of Experience (QoE) by 29% but also reduces the computational parameter count by approximately 25% while maintaining similar performances, enhancing users' immersive experiences in vehicular metaverses.

In this paper, we propose a novel federated framework for constructing the digital twin (DT) model, referring to a living and self-evolving visualization model empowered by artificial intelligence, enabled by distributed sensing under edge-cloud collaboration. In this framework, the DT model to be built at the cloud is regarded as a global one being split into and integrating from multiple functional components, i.e., partial-DTs, created at various edge servers (ESs) using feature data collected by associated sensors. Considering time-varying DT evolutions and heterogeneities among partial-DTs, we formulate an online problem that jointly and dynamically optimizes partial-DT assignments from the cloud to ESs, ES-sensor associations for partial-DT creation, and as well as computation and communication resource allocations for global-DT integration. The problem aims to maximize the constructed DT's model quality while minimizing all induced costs, including energy consumption and configuration costs, in long runs. To this end, we first transform the original problem into an equivalent hierarchical game with an upper-layer two-sided matching game and a lower-layer overlapping coalition formation game. After analyzing these games in detail, we apply the Gale-Shapley algorithm and particularly develop a switch rules-based overlapping coalition formation algorithm to obtain short-term equilibria of upper-layer and lower-layer subgames, respectively. Then, we design a deep reinforcement learning-based solution, called DMO, to extend the result into a long-term equilibrium of the hierarchical game, thereby producing the solution to the original problem. Simulations show the effectiveness of the introduced framework, and demonstrate the superiority of the proposed solution over counterparts.

With the significant advances in AI-generated content (AIGC) and the proliferation of mobile devices, providing high-quality AIGC services via wireless networks is becoming the future direction. However, the primary challenges of AIGC services provisioning in wireless networks lie in unstable channels, limited bandwidth resources, and unevenly distributed computational resources. To this end, this paper proposes a semantic communication (SemCom)-empowered AIGC (SemAIGC) generation and transmission framework, where only semantic information of the content rather than all the binary bits should be generated and transmitted by using SemCom. Specifically, SemAIGC integrates diffusion models within the semantic encoder and decoder to design a workload-adjustable transceiver thereby allowing adjustment of computational resource utilization in edge and local. In addition, aresource-aware workloadtrade-off (ROOT) scheme is devised to intelligently make workload adaptation decisions for the transceiver, thus efficiently generating, transmitting, and fine-tuning content as per dynamic wireless channel conditions and service requirements. Simulations verify the superiority of our proposed SemAIGC framework in terms of latency and content quality compared to conventional approaches.

Federated Learning (FL) has emerged as a promising framework to address data privacy concerns associated with mobile devices, in contrast to conventional Machine Learning (ML). However, traditional FL encounters significant challenges due to the heterogeneities among different clients. Clustered Federated Learning (CFL) has demonstrated effectiveness in mitigating the data heterogeneity challenge, which significantly limits a broader application of FL. Nevertheless, existing CFL approaches often tightly couple the clustering process with the main FL process, affecting the flexibility and performance of CFL. In this paper, we propose a pre-clustering-based CFL approach, named SnapCFL, which decouples the CFL process into pre-clustering and main FL stages, considering both the impact of heterogeneity on CFL accuracy and the framework's flexibility. The pre-clustering stage models the measurement of data similarity as a two-sample hypothesis testing problem to more accurately group clients and alleviate data heterogeneity. In the main FL stage, a constraint-based client selection method is employed to address the system heterogeneity problem. We conduct extensive experiments using popular datasets with various heterogeneity settings. The results demonstrate that SnapCFL achieves excellent performance in terms of accuracy and efficiency. Compared to five other state-of-the-art approaches, SnapCFL can improve model accuracy by 0.7%$\sim$36.4%, and achieve the same level of accuracy with at least 0.08× the convergence time.

With the proliferation of mobile terminals, the continuous upgrading of services, 4G LTE networks are showing signs of weakness. To enhance the capacity of wireless networks, millimeter waves are introduced to drive the evolution of networks towards multi-band 5G heterogeneous networks. The distinct propagation characteristics of mmWaves, microwaves, as well as the vastly different hardware configurations of heterogeneous base stations, make traditional access strategies no longer effective. Therefore, to narrowing the gap between theory, practice, we investigate the access strategy in multi-band 5G heterogeneous networks, taking into account the characteristics of mobile users, asynchronous switching between uplink, downlink of pico base stations, asymmetric service requirements, user communication continuity. We formulate the problem as integer nonlinear programming, prove its intractability. Thereby, we decouple it into three subproblems: user association, switch point selection, subchannel allocation, design an algorithm based on optimal matching, spectral clustering to solve it efficiently. The simulation results show that the proposed algorithm outperforms the comparison methods in terms of overall data rate, effective data rate, number of satisfied users.

Task-oriented semantic communication has emerged as a fundamental approach for enhancing performance in various communication scenarios. While recent advances in Generative Artificial Intelligence (GenAI), such as Large Language Models (LLMs), have been applied to semantic communication designs, the potential of Large Multimodal Models (LMMs) remains largely unexplored. In this paper, we investigate an LMM-based vehicle AI assistant using a Large Language and Vision Assistant (LLaVA) and propose a task-oriented semantic communication framework to facilitate efficient interaction between users and cloud servers. To reduce computational demands and shorten response time, we optimize LLaVA's image slicing to selectively focus on areas of utmost interest to users. Additionally, we assess the importance of image patches by combining objective and subjective user attention, adjusting energy usage for transmitting semantic information. This strategy optimizes resource utilization, ensuring precise transmission of critical information. We construct a Visual Question Answering (VQA) dataset for traffic scenarios to evaluate effectiveness. Experimental results show that our semantic communication framework significantly increases accuracy in answering questions under the same channel conditions, performing particularly well in environments with poor Signal-to-Noise Ratios (SNR). Accuracy can be improved by 13.4% at an SNR of 12dB and 33.1% at 10dB, respectively.

In the Metaverse, real-time, concurrent services such as virtual classrooms and immersive gaming require local graphic rendering to maintain low latency. However, the limited processing power and battery capacity of user devices make it challenging to balance Quality of Experience (QoE) and terminal energy consumption. In this paper, we investigate a multi-objective optimization problem (MOP) regarding power control and rendering capacity allocation by formulating it as a multi-objective optimization problem. This problem aims to minimize energy consumption while maximizing Meta-Immersion (MI), a metric that integrates objective network performance with subjective user perception. To solve this problem, we propose a Multi-Objective Multi-Agent Evolutionary Reinforcement Learning with User-Object-Attention (M2ERL-UOA) algorithm. The algorithm employs a prediction-driven evolutionary learning mechanism for multi-agents, coupled with optimized rendering capacity decisions for virtual objects. The algorithm can yield a superior Pareto front that attains the Nash equilibrium. Simulation results demonstrate that the proposed algorithm can generate Pareto fronts, effectively adapts to dynamic user preferences, and significantly reduces decision-making time compared to several benchmarks.

Space-air-ground (SAG) integrated heterogenous networks can provide pervasive intelligence services for various ground users (GUs). The network can help cellular networks release network resources and alleviate congestion pressure. Moreover, one important application of the network is that digital twin (DT) can enable nearly-instant wireless connectivity and highly-reliable data mapping from physical systems to digital world in a real-time fashion. The integration of SAG and DT (SAG-DT) reduces the gap between data analysis and physical status, which can further realize robust edge intelligence services. However, the random computation task arrival, time-varying channel gains, and the lack of mutual trust among ground GUs hinder better quality of service in the promising SAG-DT network. In this paper, we envision a SAG-DT integrated blockchain model to transfer the task data to the aerial network, and then perform the computation offloading, energy harvesting and privacy protection. Moreover, we propose a Lyapunov-aided multi-agent deep federated reinforcement learning (MADFRL) algorithm framework to optimize the CPU cycle frequency, the size of block, the number of DTs, and harvested energy to minimize the execution costs and privacy overhead. Extensive performance analyses indicate that the MADFRL algorithm framework can strengthen the data privacy via blockchain verification mechanism and approaches the optimal performance on the basis of lower computation complexity. Finally, simulation results corroborate that the proposed Lyapunov-aided MADFRL algorithm is superior to advanced benchmarks in terms of execution costs, task processing quantities and privacy overhead.

This paper investigates the deep learning based approaches for simultaneous wireless information and power transfer (SWIPT). The quality-of-service (QoS) constrained sumrate maximization problems are, respectively, formulated for power-splitting (PS) receivers and time-switching (TS) receivers and solved by a unified graph neural network (GNN) based model termed SWIPT net (SWIPTNet). To improve the performance of SWIPTNet, we first propose a single-type output method to reduce the learning complexity and facilitate the satisfaction of QoS constraints, and then, utilize the Laplace transform to enhance input features with the structural information. Besides, we adopt the multi-head attention and layer connection to enhance feature extracting. Furthermore, we present the implementation of transfer learning to the SWIPTNet between PS and TS receivers. Ablation studies show the effectiveness of key components in the SWIPTNet. Numerical results also demonstrate the capability of SWIPTNet in achieving nearoptimal performance with millisecond-level inference speed which is much faster than the traditional optimization algorithms. We also show the effectiveness of transfer learning via fast convergence and expressive capability improvement.

This paper investigates the graph neural network (GNN)-enabled beamforming design for interference channels. We propose a model termed interference channel GNN (ICGNN) to solve a quality-of-service constrained energy efficiency maximization problem. The ICGNN is two-stage, where the direction and power parts of beamforming vectors are learned separately but trained jointly via unsupervised learning. By formulating the dimensionality of features independent of the transceiver pairs, the ICGNN is scalable with the number of transceiver pairs. Besides, to improve the performance of the ICGNN, the hybrid maximum ratio transmission and zero-forcing scheme reduces the output ports, the feature enhancement module unifies the two types of links into one type, the subgraph representation enhances the message passing efficiency, and the multi-head attention and residual connection facilitate the feature extracting. Furthermore, we present the over-the-air distributed implementation of the ICGNN. Ablation studies validate the effectiveness of key components in the ICGNN. Numerical results also demonstrate the capability of ICGNN in achieving near-optimal performance with an average inference time less than 0.1 ms. The scalability of ICGNN for unseen problem sizes is evaluated and enhanced by transfer learning with limited fine-tuning cost. The results of the centralized and distributed implementations of ICGNN are illustrated.

Smart grid, through networked smart meters employing the non-intrusive load monitoring (NILM) technique, can considerably discern the usage patterns of residential appliances. However, this technique also incurs privacy leakage. To address this issue, we propose an innovative scheme based on adversarial attack in this paper. The scheme effectively prevents NILM models from violating appliance-level privacy, while also ensuring accurate billing calculation for users. To achieve this objective, we overcome two primary challenges. First, as NILM models fall under the category of time-series regression models, direct application of traditional adversarial attacks designed for classification tasks is not feasible. To tackle this issue, we formulate a novel adversarial attack problem tailored specifically for NILM and providing a theoretical foundation for utilizing the Jacobian of the NILM model to generate imperceptible perturbations. Leveraging the Jacobian, our scheme can produce perturbations, which effectively misleads the signal prediction of NILM models to safeguard users' appliance-level privacy. The second challenge pertains to fundamental utility requirements, where existing adversarial attack schemes struggle to achieve accurate billing calculation for users. To handle this problem, we introduce an additional constraint, mandating that the sum of added perturbations within a billing period must be precisely zero. Experimental validation on real-world power datasets REDD and U.K.-DALE demonstrates the efficacy of our proposed solutions, which can significantly amplify the discrepancy between the output of the targeted NILM model and the actual power signal of appliances, and enable accurate billing at the same time. Additionally, our solutions exhibit transferability, making the generated perturbation signal from one target model applicable to other diverse NILM models.

Underwater target hunting (UTH) is a critical and complex mission involving the search, monitoring, and hunting of targets in an underwater environment. However, the unpredictable trajectories and flexibility of these targets, along with complex underwater environments, significantly impede the efficiency and success of traditional schemes that depend solely on unmanned underwater vehicles (UUVs). Consequently, this paper presents the “3U network”, a novel heterogeneous framework integrating unmanned aerial vehicles (UAVs), unmanned surface vehicles (USVs), and UUVs for UTH. Within this framework, a UAV searches and monitors the target, a USV acts as a communication relay, and a swarm of UUVs hunts the target. Moreover, to improve the timeliness of target search, we propose the age of information (AoI)-based UAV search strategy. Additionally, we construct a constrained multi-objective optimization problem aiming to minimize energy consumption and mission duration by optimizing vehicles' trajectories, considering mobility limitations, safety, and connectivity constraints. To tackle this problem, we design an AoI- and energy-aware deep reinforcement learning (DRL) algorithm to optimize control policies for heterogeneous vehicles. The experimental results demonstrate that the proposed scheme outperforms the baseline schemes in terms of energy consumption, and mission duration and success rates.

With an extensive increment of computation demands, the aerial multi-access edge computing (MEC), mainly based on unmanned aerial vehicles (UAVs) and high altitude platforms (HAPs), plays significant roles in future network scenarios. In detail, UAVs can be flexibly deployed, while HAPs are characterized with large capacity and stability. Hence, in this paper, we provide a hierarchical model composed of an HAP and multi-UAVs, to provide aerial MEC services. Moreover, considering the errors of channel state information from unpredictable environmental conditions, we formulate the problem to minimize the total energy cost with the chance constraint, which is a mixed-integer nonlinear problem with uncertain parameters and intractable to solve. To tackle this issue, we optimize the UAV deployment via the weighted K-means algorithm. Then, the chance constraint is reformulated via the distributionally robust optimization (DRO). Furthermore, based on the conditional value-at-risk mechanism, we transform the DRO problem into a mixed-integer second order cone programming, which is further decomposed into two subproblems via the primal decomposition. Moreover, to alleviate the complexity of the binary subproblem, we design a binary whale optimization algorithm. Finally, we conduct extensive simulations to verify the effectiveness and robustness of the proposed schemes by comparing with baseline mechanisms.

By synergistically integrating mobile networks and embodied artificial intelligence (AI),mobileembodiedAInetworks (MEANETs) represent an advanced paradigm that facilitates autonomous, context-aware, and interactive behaviors within dynamic environments. Nevertheless, the rapid development of MEANETs is accompanied by challenges in trustworthiness and operational efficiency. Fortunately, blockchain technology, with its decentralized and immutable characteristics, offers promising solutions for MEANETs. However, existing block propagation mechanisms suffer from challenges such as low propagation efficiency and weak security for block propagation, which results in delayed transmission of messages or vulnerability to malicious tampering, potentially causing severe accidents in blockchain-enabled MEANETs. Moreover, current block propagation strategies cannot effectively adapt to real-time changes of dynamic topology in MEANETs. Therefore, in this paper, we propose a graph Resfusion model-based trustworthy block propagation optimization framework for consortium blockchain-enabled MEANETs. Specifically, we propose an innovative trust calculation mechanism based on the trust cloud model, which comprehensively accounts for randomness and fuzziness in the validator trust evaluation. Furthermore, by leveraging the strengths of graph neural networks and diffusion models, we develop a graph Resfusion model to effectively and adaptively generate the optimal block propagation trajectory. Simulation results demonstrate that the proposed model outperforms other routing mechanisms in terms of block propagation efficiency and trustworthiness. Additionally, the results highlight its strong adaptability to dynamic environments, making it particularly suitable for rapidly changing MEANETs.

Efficient wireless resource allocation is essential for supporting multi-vehicle cooperation. The service data exchanged among intelligent vehicles is typically diverse, with varying transmission requirements that shift according to applications and traffic conditions, leading to major fluctuation in communication situations. Existing multi-agent reinforcement learning based resource allocation methods are often inefficient in handling such nonstationary communication situations due to their rigid cooperation patterns. To this end, we propose a ROle-TRansformable multi-agent resource allocation method, named ROTR. This method adopts a hierarchical decision-making process, where a high-level agent at a base station (BS) dynamically plans and distributes cooperation roles (CRs) and cooperation behaviors (CBs) in response to fluctuating communication situations. The Low-level agents within the transmitting vehicles (TVs) perform role transformations based on the assigned CRs and subsequently receive behavioral guidance according to CBs, enabling dynamic adjustments in cooperation patterns to adapt to variable communication situations and make resource allocation decisions. Additionally, we introduce a non-BS-assisted mode based on policy distillation, which enables a seamless transition to independent operation without the BS, relying solely on local states to generate CRs and CBs, thereby facilitating global resource cooperation. Extensive simulation experiments demonstrate that the proposed framework optimizes resource efficiency in nonstationary vehicular communications.

Semantic communication (SemCom), a paradigm that emphasizes conveying the meaning of information, faces challenges in precise reasoning in semantic coding models. Knowledge graphs (KGs) offer a potential solution by providing structured triples (entities and relations), enabling inference via entity attributes and relational logic. Several key challenges exist in leveraging KGs within SemCom. The first challenge lies in developing methods to create semantic representations aligning and integrating source data and KG information. Second, reconstructing the original data using KGs becomes challenging particularly under poor communication conditions. Moreover, integrating KGs with source data inevitably increases the transmission overhead. In this paper, we propose a novel SemCom framework named KG-SemCom with sophisticated KG-based semantic encoding and decoding designs to solve these challenges. This framework aligns KG entities with message tokens, and then encodes messages into a semantic fusion of contextual and knowledge-based information. Furthermore, KG-SemCom can utilize the KG and contextual relationships to assist in predicting incomplete or distorted messages during the decoding process. Finally, simulation results demonstrate that KG-SemCom achieves higher accuracy and greater robustness compared to existing benchmarks without incorporating KGs, especially in challenging communication environments.

Optimization is crucial for the efficiency and reliability of multi-access edge computing (MEC) networks. Many optimization problems in this field are NP-hard and do not have effective approximation algorithms. Consequently, there is often a lack of optimal (ground-truth) data, which limits the effectiveness of traditional deep learning approaches. Most existing learning-based methods require a large amount of optimal data and do not leverage the potential advantages of using suboptimal data, which can be obtained more efficiently. To illustrate this point, we focus on the multi-server multi-user computation offloading (MSCO) problem, a common issue in MEC networks that lacks efficient optimal solution methods. In this paper, we introduce the graph diffusion-based solution generator (GDSG), designed to work with suboptimal datasets while still achieving convergence to the optimal solution with high probability. We reformulate the network optimization challenge as a distribution-learning problem and provide a clear explanation of how to learn from suboptimal training datasets. We develop GDSG, a multi-task diffusion generative model that employs a graph neural network (GNN) to capture the distribution of high-quality solutions. Our approach includes a straightforward and efficient heuristic method to generate a sufficient amount of training data composed entirely of suboptimal solutions. In our implementation, we enhance the GNN architecture to achieve better generalization. Moreover, the proposed GDSG can achieve nearly 100% task orthogonality, which helps prevent negative interference between the discrete and continuous solution generation training objectives. We demonstrate that this orthogonality arises from the diffusion-related training loss in GDSG, rather than from the GNN architecture itself. Finally, our experiments show that the proposed GDSG outperforms other benchmark methods on both optimal and suboptimal training datasets. Regarding the minimization of computation offloading costs, GDSG achieves savings of up to 56.62% on the ground-truth training set and 41.06% on the suboptimal training set compared to existing discriminative methods.

The rapid advancement of Artificial Intelligence (AI) has introduced Deep Neural Network (DNN)-based tasks to the ecosystem of vehicular networks. These tasks are often computation-intensive, requiring substantial computation resources, which are beyond the capability of a single vehicle. To address this challenge, Vehicular Edge Computing (VEC) has emerged as a solution, offering computing services for DNN-based tasks through resource pooling via Vehicle-to-Vehicle/Infrastructure (V2V/V2I) communications. In this paper, we formulate the problem of joint DNN partitioning, task offloading, and resource allocation in VEC as a dynamic long-term optimization. Our objective is to minimize the DNN-based task completion time while guaranteeing the system stability over time. To this end, we first leverage a Lyapunov optimization technique to decouple the original long-term optimization with stability constraints into a per-slot deterministic problem. Afterwards, we propose a Multi-Agent Diffusion-based Deep Reinforcement Learning (MAD2RL) algorithm, incorporating the innovative use of diffusion models to determine the optimal DNN partitioning and task offloading decisions. Furthermore, we integrate convex optimization techniques into MAD2RL as a subroutine to allocate computation resources, enhancing the learning efficiency. Through simulations under real-world movement traces of vehicles, we demonstrate the superior performance of our proposed algorithm compared to existing benchmark solutions.

The rapid advancement of immersive technologies has propelled the development of the Metaverse, where the convergence of virtual and physical realities necessitates the generation of high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due to the limited computing resources of edge devices and the dynamic nature of wireless networks. This paper proposes a novel framework that integrates contract-inspired contest theory, Deep Reinforcement Learning (DRL), and GDMs to optimize image generation in these resource-constrained environments. The framework addresses the critical challenges of resource allocation and semantic data transmission quality by incentivizing edge devices to efficiently transmit high-quality semantic data, which is essential for creating realistic and immersive images. The use of contest and contract theory ensures that edge devices are motivated to allocate resources effectively, while DRL dynamically adjusts to network conditions, optimizing the overall image generation process. Experimental results demonstrate that the proposed approach not only improves the quality of generated images but also achieves superior convergence speed and stability compared to traditional methods. This makes the framework particularly effective for optimizing complex resource allocation tasks in mobile edge Metaverse applications, offering enhanced performance and efficiency in creating immersive virtual environments.

Federated Learning (FL) allows multiple clients to collaboratively train machine learning models without the need to share their local private data. As a result, it can effectively address the issue of data fragmentation. Nevertheless, insufficient evaluation of individual contributions and the lack of protections for both the intellectual property rights (IPR) of models and client privacy can greatly reduce clients' motivations in federated training. To address these challenges, this paper introduces the Traceable Contribution Evaluation and Model Ownership Protection (TraCemop) framework for federated learning, which allows each client to swiftly assess the contributions of others in each round, with integrated support for the traceability of evaluation results. To safeguard the intellectual property of models, a collective watermark is embedded in the global model. Additionally, a secure mechanism for verifying model ownership is also available in case of disputes. Security analysis indicates that TraCemop is capable of resisting data reconstruction attacks as well as various types of model copyright infringements. Finally, we evaluate the proposed framework using two commonly-used datasets, and the experimental results show a significant improvement in the efficiency of contribution evaluation compared to existing methods. Meanwhile, IPR infringement tests on TraCemop reveal that the proposed framework is resilient against malicious efforts to monopolize model ownership.

Artificial intelligence-generated content (AIGC) has been proposed as a solution to meet the requirements of ultra-reliable, secure, and privacy-preserving connectivity in human digital twin (HDT) networks. In such an AIGC-enhanced HDT, contents representing the true statuses of physical twins are generated in the virtual environment for the immediate update and evolution of the corresponding virtual twins (VTs). However, adopting a distributed AIGC in HDT presents several challenges, including the need for personalized VTs, data privacy concerns, and insufficient contextual understanding. This paper introduces a multi-layer federated semantic learning framework to address these challenges, incorporating batch learning to meet the training requirements for semantic-channel encoders and decoders. Furthermore, we introduce a novel user association framework to maximize the overall system performance under shard formation constraints. We then formulate a long-term joint optimization problem for user selection over finite learning periods. A novel Lyapunov-based online optimization strategy was proposed to mitigate the impact of time-varying and unpredictable training conditions. Additionally, we introduce a multi-arm bandit-based method and a context-centric user selection approach to solve the optimization problem. The results demonstrate that the proposed user association framework addresses the limitations of existing approaches, thereby improving the overall performance of the multi-shard AIGC-enhanced HDT.

Cooperative reconfigurable intelligent surfaces (RISs) are promising technologies for 6 G networks to support a great number of users. Compared with the fixed RISs, the properly deployed RISs may improve the communication performance with less communication energy consumption, thereby improving the energy efficiency. In this paper, we consider a cooperative unmanned aerial vehicle-mounted RISs (UAV-RISs)-assisted cellular network, where multiple RISs are carried and enhanced by UAVs to serve multiple ground users (GUs) simultaneously such that achieving the three-dimensional (3D) mobility and opportunistic deployment. Specifically, we formulate an energy-efficient communication problem based on multi-objective optimization framework (EEComm-MOF) to jointly consider the beamforming vector of base station (BS), the location deployment and the discrete phase shifts of UAV-RIS system so as to simultaneously maximize the minimum available rate over all GUs, maximize the total available rate of all GUs, and minimize the total energy consumption of the system, while the transmit power constraint of BS is considered. To comprehensively solve EEComm-MOF which is an NP-hard and non-convex problem with constraints, a non-dominated sorting genetic algorithm-II with a continuous solution processing mechanism, a discrete solution processing mechanism, and a complex solution processing mechanism (INSGA-II-CDC) is proposed. Simulations results demonstrate that the proposed INSGA-II-CDC can solve EEComm-MOF effectively and outperforms other benchmarks under different parameter settings. Moreover, the stability of INSGA-II-CDC and the effectiveness of the improved mechanisms are verified. Finally, the implementability analysis of the algorithm is given.

Human digital twin bridges humans with digital avatars in the fabric metaverse, assisting users and healthcare professionals with real-time visualization, analysis, and prediction of personal data sensed by fabric sensors. The human digital twin-assisted healthcare monitoring (HHM) service refreshment refers to sending personal health data to corresponding services hosted on nearby edge servers and receiving the results to update local digital avatars continuously. However, the malicious nature and resource limitations of edge servers may lead to user privacy leaks and refreshment timeout, thereby impacting diagnostics. In this paper, we investigate a novel privacy-enhanced HHM service refreshment maximization problem in the fabric metaverse by considering privacy data encryption, model compression, and personalized user requirements. To this end, we first formulate the above issue as an Integer Linear Programming (ILP) problem, and prove its NP-hardness. Then, a resource scheduler named Wiper is designed, consisting of a shallow-deep distiller and an agile refresher library. To enable efficient inference while preserving user privacy, the former replaces violation modules in existing models with approximations and conducts shallow distillation on model layers to meet operation type and depth limits of homomorphic encryption, and then deep distillation on model parameters to decrease end-to-end refreshment delay. Finally, to satisfy user requirements on accuracy and delay during encrypted refreshments while maximizing the throughput of HHM services in offline and online situations with different problem scales, a series of HHM service refreshment algorithms are merged into the latter, including exact, performance-guaranteed approximation, and residual diffusion reinforcement learning algorithms. Theoretical analyses and experiments demonstrate that our algorithms are promising compared with baseline algorithms.

The rise of real-time applications, services has made Multi-access Edge Computing (MEC) essential for delivering low-latency, high-performance computing. The effectiveness of MEC, however, is largely contingent on the efficient pre-deployment of services. Despite its importance, efficient service pre-deployment is challenged by the inherent unpredictability of user mobility, the fluctuating conditions of network environments. Accurately predicting user locations, dynamically optimizing resource allocation across geographically distributed MEC servers are complex tasks that are essential to minimizing latency, maximizing data transmission efficiency. The variability in user movement patterns, network bandwidth further exacerbates these challenges, often leading to increased latency, diminished performance, which can negate the advantages offered by MEC. To address these challenges, this paper introduces a novel edge service pre-deployment scheme based on location prediction (ESPD-LP). The ESPD-LP scheme leverages historical user trajectory data to predict future locations, facilitating proactive, strategic resource allocation via a user-centric bidirectional matching algorithm across multiple MEC servers. By pre-deploying services in anticipation of user needs, this approach optimizes data transmission rates, reduces pre-deployment latency, significantly enhancing the overall performance of MEC systems. A comprehensive analysis reveals that the ESPD-LP scheme consistently outperforms similar approaches, with a 41% increase in data transmission rates, a 31% reduction in pre-deployment latency compared to the JO-CDSD, MEC-RDESN schemes, demonstrating consistently superior performance.

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) is emerging as a promising paradigm to provide aerial-terrestrial computing services in close proximity to mobile devices (MDs). However, meeting the demands of computation-intensive and delay-sensitive tasks for MDs poses several challenges, including the demand-supply contradiction between MDs and MEC servers, the demand-supply discrepancy between MDs and MEC servers, the trajectory control requirements on energy efficiency and timeliness, and the different time-scale dynamics of the network. To address these issues, we first present a hierarchical architecture by incorporating terrestrial-aerial computing capabilities and leveraging UAV flexibility. Furthermore, we formulate a joint computing resource allocation, computation offloading, and trajectory control problem to maximize the system utility. Since the problem is a non-convex and NP-hard mixed integer nonlinear programming (MINLP), we propose a two-timescale joint computing resource allocation, computation offloading, and trajectory control (TJCCT) approach for solving the problem. In the short timescale, we propose a price-incentive model for on-demand computing resource allocation and a matching mechanism-based method for computation offloading. In the long timescale, we propose a convex optimization-based method for UAV trajectory control. Besides, we theoretically prove the stability and polynomial complexity of TJCCT. Extensive simulation results demonstrate that the proposed TJCCT is able to achieve superior performances in terms of the system utility, average processing rate, average completion delay, average completion ratio, and average cost, while meeting the energy constraints despite the trade-off of the increased energy consumption.

Autonomous aerial vehicles (AAVs) have emerged as the potential aerial base stations (BSs) to improve terrestrial communications. However, the limited onboard energy and antenna power of a AAV restrict its communication range and transmission capability. To address these limitations, this work employs collaborative beamforming through a AAV-enabled virtual antenna array to improve transmission performance from the AAV to terrestrial mobile users, under interference from non-associated BSs and dynamic channel conditions. Specifically, we introduce a memory-based random walk model to more accurately depict the mobility patterns of terrestrial mobile users. Following this, we formulate a multi-objective optimization problem (MOP) focused on maximizing the transmission rate while minimizing the flight energy consumption of the AAV swarm. Given the NP-hard nature of the formulated MOP and the highly dynamic environment, we transform this problem into a multi-objective Markov decision process and propose an improved evolutionary multi-objective reinforcement learning algorithm. Specifically, this algorithm introduces an evolutionary learning approach to obtain the approximate Pareto set for the formulated MOP. Moreover, the algorithm incorporates a long short-term memory network and hyper-sphere-based task selection method to discern the movement patterns of terrestrial mobile users and improve the diversity of the obtained Pareto set. Simulation results demonstrate that the proposed method effectively generates a diverse range of non-dominated policies and outperforms existing methods. Additional simulations demonstrate the scalability and robustness of the proposed CB-based method under different system parameters and various unexpected circumstances.

Multi-access edge computing (MEC) is emerging as a promising paradigm to provide flexible computing services close to user devices (UDs). However, meeting the computation-hungry and delay-sensitive demands of UDs faces several challenges, including the resource constraints of MEC servers, inherent dynamic and complex features in the MEC system, and difficulty in dealing with the time-coupled and decision-coupled optimization. In this work, we first present an edge-cloud collaborative MEC architecture, where the MEC servers and cloud collaboratively provide offloading services for UDs. Moreover, we formulate an energy-efficient and delay-aware optimization problem (EEDAOP) to minimize the energy consumption of UDs under the constraints of task deadlines and long-term queuing delays. Since the problem is proved to be non-convex mixed integer nonlinear programming (MINLP), we propose an online joint communication resource allocation and task offloading approach (OJCTA). Specifically, we transform EEDAOP into a real-time optimization problem by employing the Lyapunov optimization framework. Then, to solve the real-time optimization problem, we propose a communication resource allocation and task offloading optimization method by employing the Tammer decomposition mechanism, convex optimization method, bilateral matching mechanism, and dependent rounding method. Simulation results demonstrate that the proposed OJCTA can achieve superior system performance compared to the benchmark approaches.

Using the wireless waveform superposition property, over-the-air computation (OAC) enables federated learning (FL) to achieve fast model aggregation. However, this computing paradigm is vulnerable to poisoning attacks due to the openness of a wireless channel over time, where malicious mobile devices can introduce cumulative errors for the global FL model in a time-varying wireless environment for each communication round. This article presents a trust online OAC (TO-OAC) scheme to minimize impacts on the global model introduced by malicious devices adjusting to dynamic attack and wireless channel fluctuations over time. TO-OAC achieves this by utilizing trustworthy security quantification of OAC for each FL training round. To optimize the cumulative training loss at the aggregation node with the long-term power and trust constraints of mobile devices, we propose a joint trust, power, and channel-aware algorithm to flexibly update local and global models in response to the dynamic changes in the wireless and secure environment. We analyze the performance limits for the aggregation of trust models, considering metrics for computation and communication through time. We then propose another trust online regularization over-the-air computation (TOR-OAC) as an improved version of the TO-OAC scheme to decrease convergence time while ensuring long-term trust and power limitation. Experimental results performed on real-life datasets show that the two proposed schemes (TO-OAC and TOR-OAC) outperform prior works, especially in noisy, time-varying wireless channels and malicious attacks.

Blockchain-based federated learning (BFL) has gained attention for its potential to establish decentralized trust. While existing research primarily focuses on personalized frameworks for various applications, essential aspects including incentive mechanisms—critical for ensuring stable system operation—remain under-explored. To bridge this gap, we propose a game-theoretic incentive mechanism designed to foster active participation in BFL tasks. Specifically, we model a BFL system comprising a model owner (MO), i.e., task publisher, multiple miners, and training terminals, framing their interactions through two-tier Stackelberg games. In the first-tier game, the MO designs reward strategies to incentivize training terminals to contribute more data, enhancing model accuracy. The second-tier game introduces a multi-leader multi-follower Stackelberg game, enabling miners to set model packaging prices based on competitors' strategies and anticipated user behavior. By deriving the Stackelberg equilibrium, we identify optimal strategies for all participants, leading to an incentive mechanism balancing individual interests with overall performance. Compared to its benchmarks, our incentive mechanism offers 5.8% and 53.4% higher utilities in the two games compared to its alternatives, accelerating convergence and improving accuracy.

While unmanned aerial vehicles (UAVs) with flexible mobility are envisioned to enhance physical layer security in wireless communications, the efficient security design that adapts to such high network dynamics is rather challenging. The conventional approaches extended from optimization perspectives are usually quite involved, especially when jointly considering factors in different scales such as deployment and transmission in UAV-related scenarios. In this paper, we address the UAV-enabled multi-user secure communications by proposing a deep graph reinforcement learning framework. Specifically, we reinterpret the security beamforming as a graph neural network (GNN) learning task, where mutual interference among users is managed through the message-passing mechanism. Then, the UAV deployment is obtained through soft actor-critic reinforcement learning, where the GNN-based security beamforming is exploited to guide the deployment strategy update. Simulation results demonstrate that the proposed approach achieves near-optimal security performance and significantly enhances the efficiency of strategy determination. Moreover, the deep graph reinforcement learning framework offers a scalable solution, adaptable to various network scenarios and configurations, establishing a robust basis for information security in UAV-enabled communications.

The Service Function Chain (SFC) leverages Network Function Virtualization (NFV) and Software-Defined Networking (SDN) for flexible deployment, creating customized service chains tailored to specific applications. As NFV and SDN technologies play crucial roles in the SFC implementation, any security risk that arises in an NFV/SDN network can potentially pose a threat to SFC. Thus, SFC becomes vulnerable to network security attacks. To address this, intrinsic security technologies, including moving target defense and mimic defense, offer proactive protection against both known and unknown threats. It is expected to break through traditional security protection mechanisms such as “enhanced”, “plug-in” and “passive” defense. This paper proposes an intrinsic dynamic defense architecture to equip SFC with active defense capabilities, shifting from passive reactive mechanism based on prior knowledge to an active defense against various attacks. The architecture comprises two models and five modules, including a sub-pool partitioning algorithm that enhances heterogeneity across sub-pools by splitting the heterogeneous replica pool into several sub-pools among replica VNFs. To meet Quality of Service (QoS) requirements like latency, cost, and security, we formulate a multi-objective optimization problem with three objectives: latency, cost, and defense success rate. Following that, we propose a dynamic Deep Reinforcement Learning (DRL)-based deployment algorithm. This algorithm selects appropriate VNFs based on heterogeneity and historical information, improving SFC and VNF security against external attacks. Extensive experiments validate that our architecture significantly enhances network security, provided that this improvement comes at the expense of limited cost and latency.

The explosive growth of the Internet of Things (IoT) has dramatically increased the demand for secure mechanisms to protect against unauthorized access and attacks. Traditionally, expensive Software-Defined Radios (SDRs) have been utilized to gather IoT physical features, which are critical for reliable authentication. However, the high cost of SDRs makes them impractical for widespread deployment across the vast and diverse IoT ecosystem. In contrast, this paper presents AUTHFi, a novel cross-technology device authentication framework that transforms the SDR approach for collecting and authenticating IoT device signals (e.g., ZigBee and Bluetooth) by utilizing commercial WiFi devices. Specifically, AUTHFi leverages the recent advances in Cross-Technology Communication (CTC) to reconstruct the partial waveform of IoT transmission, thus eliminating the requirement for expensive SDRs. AUTHFi requires us to address several unique challenges. First, AUTHFi compensates for signal losses of the partial waveform to get more signal information. Then, it introduces an enhanced Carrier Frequency Offset (CFO) estimation and a fusion neural network that combines CFO and the reconstructed waveform for accurate device authentication. We implement AUTHFi based on RTL8812au (commodity WiFi) and CC2652P (commodity ZigBee/Bluetooth). Our thorough evaluation confirms that AUTHFi offers reliable authentication under various settings, achieving a maximum accuracy of 94.2%.

Vehicle Edge Computing (VEC) assists vehicles in performing latency-sensitive tasks by deploying resources near the vehicle. Designing an incentive mechanism for vehicles and VEC is crucial for realizing an intelligent transmission system. Considering the rationality of resource allocation, we model the utility functions of the VEC and the vehicle, which are used as optimization objectives. Specifically, the VEC allocates resources through pricing to maximize revenue under resource-constrained conditions, and the vehicle weighs payments against energy consumption to determine offloading and resource allocation. Given the vehicle movement and the variable channel state, we use the Deep Reinforcement Learning (DRL) algorithm to solve these optimization problems. To reduce the learning difficulty of the DRL algorithm in complex VEC scenarios with multiple optimization variables, we propose a Pricing-Driven Resource Allocation (PDRA) algorithm that performs mobility-aware task offloading and calculates the optimal values of the optimization variables in the utility function of the vehicle to reduce the decision dimension. Furthermore, we also propose a DRL-based Pricing-Driven Dynamic Resource Allocation (DPDDRA) algorithm to achieve efficient resource allocation. Extensive experimental results show that the proposed algorithms can reduce the learning difficulty while maximizing VEC and vehicle revenue in complex VEC scenarios.

Wireless sensing systems have been employed in the field of healthcare, environment monitoring, and smart agriculture, etc. Since the freshness and accuracy indicators of the sensing data are critical to wireless sensing systems, it is of great significance to ensure their performances simultaneously, i.e., the Age of Information (AoI) and information entropy of the sensing data should be jointly optimized. In this regard, we first establish the wireless sensing system models, including AoI and information entropy expressions. Next, from the information entropy viewpoint, we theoretically analyze an impact of the AoI on data accuracy. Then, we formulate the joint optimization problem of AoI, information entropy, and sensing energy consumption. Furthermore, we propose two numerical algorithms to solve the formulated problem in the known or unknown transmission environment, respectively. Finally, we evaluate the correctness and effectiveness of our proposals under various parameter settings, where the proposed scheme can obtain a better sum-weighted performance on AoI, information entropy, and sensing energy consumption than baselines in the literature.

To reduce redundant traffic transmission in both wired and wireless networks, optimal content placement problem naturally occurring in many applications is studied. In this paper, considering the limited cache capacity, unknown popularity distribution and non-stationary user demands, we address this problem by jointly optimizing content caching and routing with the objective of minimizing transmission cost. By optimizing the routing with theroute-to-least cost-cachepolicy, the content caching process is modeled as a Markov decision process (MDP), aiming to maximize caching reward. However, the optimization problem consists of multiple nodes selecting caching contents, which leads to the combinatorial increase of the number of action dimensions with the number of possible actions. To handle this curse of dimensionality, we propose an intelligent caching algorithm by embedding action branching architecture into a dueling double deep Q-network (D3QN) to optimize caching decisions, and thus the agent at the controller can adaptively learn and track the underlying dynamics. Considering the independence of each branch, a marginal gain-based replacement rule is proposed to satisfy cache capacity constraint. Our simulation results show that compared with the prior art, the caching reward and hit rate of the proposed algorithm are increased by 35.3% and 33.6% respectively on average.

Mobile edge computing (MEC) is a promising technology that enhances the efficiency of mobile blockchain networks, by enabling miners, often acted by mobile users (MUs) with limited computing resources, to offload resource-intensive mining tasks to nearby edge computing servers. Collaborative block mining can further boost mining efficiency by allowing multiple miners to form coalitions, pooling their computing resources and transaction data together to mine new blocks collaboratively. Therefore, an MEC-assisted collaborative blockchain network can leverage the strengths of both technologies, offering improved efficiency, security, and scalability for blockchain systems. While existing research in this area has mainly focused on the singlecoalition collaboration mode, where each miner can only join one coalition, this work explores a more comprehensive multicoalition collaboration mode, which allows each miner to join multiple coalitions. To analyze the behavior of miners and the edge computing service provider (ECP) in this scenario, we propose a novel two-stage Stackelberg game. In Stage I, the ECP, as the leader, determines the prices of computing resources for all MUs. In Stage II, each MU decides the coalitions to join, resulting in an overlapping coalition formation (OCF) game; Subsequently, each coalition decides how many edge computing resources to purchase from the ECP, leading to an edge resource competition (ERC) game. We derive the closed-form Nash equilibrium for the ERC game, based on which we further propose an OCFbased alternating algorithm to achieve a stable coalition structure for the OCF game and develop a near-optimal pricing strategy for the ECP's resource pricing problem. Simulation results show that the proposed multi-coalition collaboration mode can improve the system efficiency by 12.64% ∼ 17.63%, compared to the traditional single-coalition collaboration mode.

Multi-task semantic communication can serve multiple learning tasks using a shared encoder model. Existing models have overlooked the intricate relationships between features extracted during an encoding process of tasks. This paper presents a new graph attention inter-block (GAI) module to the encoder/ transmitter of a multi-task semantic communication system, which enriches the features for multiple tasks by embedding the intermediate outputs of encoding in the features, compared to the existing techniques. The key idea is that we interpret the outputs of the intermediate feature extraction blocks of the encoder as the nodes of a graph to capture the correlations of the intermediate features. Another important aspect is that we refine the node representation using a graph attention mechanism to extract the correlations and a multi-layer perceptron network to associate the node representations with different tasks. Consequently, the intermediate features are weighted and embedded into the features transmitted for executing multiple tasks at the receiver. Experiments demonstrate that the proposed model surpasses the most competitive and publicly available models by 11.4% on the CityScapes 2Task dataset and outperforms the established state-of-the-art by 3.97% on the NYU V2 3Task dataset, respectively, when the bandwidth ratio of the communication channel (i.e., compression level for transmission over the channel) is as constrained as$\frac{1}{12}$.

Due to flexibility and low-cost, unmanned aerial vehicles (UAVs) are increasingly crucial for enhancing coverage and functionality of wireless networks. However, incorporating UAVs into next-generation wireless communication systems poses significant challenges, particularly in sustaining high-rate and long-range secure communications against eavesdropping attacks. In this work, we consider a UAV swarm-enabled secure surveillance network system, where a UAV swarm forms a virtual antenna array to transmit sensitive surveillance data to a remote base station (RBS) via collaborative beamforming (CB) so as to resist mobile eavesdroppers. Specifically, we formulate an aerial secure communication and energy efficiency multi-objective optimization problem (ASCEE-MOP) to maximize the secrecy rate of the system and to minimize the flight energy consumption of the UAV swarm. To address the non-convex, NP-hard and dynamic ASCEE-MOP, we propose a generative diffusion model-enabled twin delayed deep deterministic policy gradient (GDMTD3) method. Specifically, GDMTD3 leverages an innovative application of diffusion models to determine optimal excitation current weights and position decisions of UAVs. The diffusion models can better capture the complex dynamics and the trade-off of the ASCEE-MOP, thereby yielding promising solutions. Simulation results highlight the superior performance of the proposed approach compared with traditional deployment strategies and some other deep reinforcement learning (DRL) benchmarks. Moreover, performance analysis under various parameter settings of GDMTD3 and different numbers of UAVs verifies the robustness of the proposed approach.

In the 6G era, user demand for low-latency, cost-effective extreme services such as extended reality (XR) and holographic communications has significantly increased. Multi-domain networks, known for their vast capacity and coverage, are essential in fulfilling the growing demand for high-performance services. Despite their potential, these networks face challenges with domain isolation, requiring a software defined network (SDN) controller for inter-domain communication. Network function virtualization (NFV) enhances flexibility of service delivery with customizable service function chain (SFC), yet prior research falls short in delivering low-latency, cost-efficient services in multi-domain NFV networks alongside an unreasonable assumption that software on physical nodes can support the execution of all virtualization network functions (VNFs). In this paper, we study the problem of SFC deployment with VNF-dependent software migration (SD-VDSM) in multi-domain networks. Particularly, we first formulate the problem by setting an objective to minimize the end-to-end communication delay and the associated costs of service provisioning, while simultaneously ensuring load balancing across multi-domain networks. However, complexity of the issue escalates to an intractable level due to the intertwined nature of SFC deployment strategies and VNF-dependent software migration tactics, which mutually influence each other intricately. To tackle this issue, we propose an innovative heuristic algorithm, designated as the Joint SFC Deployment with VNF-Dependent Software Migration Algorithm (JSD-VDSMA). Comprising three fundamental steps, this algorithm is crafted to adeptly resolve the complexities of service provisioning across multi-domain networks. A suite of rigorous experimental assessments is detailed, demonstrating the capability of our proposed JSD-VDSMA. Through these comparative analyses, we demonstrate its effectiveness not only to increase the service acceptance rate but also to diminish both the end-to-end communication delay and resource utilization costs in comparison to its counterparts.

With the widespread deployment of Low Earth Orbit (LEO) satellites, they generate a vast amount of data. This data has been instrumental in supporting machine learning (ML) in various terrestrial services to address global challenges such as monitoring climate change and natural disasters. However, many national regulations restrict the direct transmission of satellite data to ground stations (GSs). Therefore, ground-assisted satellite federated learning (FL) has emerged as a paradigm to safeguard data privacy by transferring model parameters instead of raw data for collaborative training. At present, the existing groundassisted satellite FL methods encounter practical challenges: 1) The dynamic environment of LEO satellites results in continuous changes in the types of data collected by satellites, making it difficult for traditional FL models to adapt to these changes. This can lead to a deterioration in model accuracy over extended periods of model training. 2) Communication between satellites and GS is affected by atmospheric interference and weather factors, resulting in increased transmission delays and affecting the realtime efficiency of the FL system. In response to these challenges, we propose a dynamic, efficient, and distributed ground-assisted LEO satellite federated learning (DEDFL) framework to improve model accuracy and reduce satellite communication delays. In DEDFL, we design a Balanced Class Memory Extraction and an information playback strategy that enables the onboard FL model to adapt to changing satellite data types, thus achieving a performance balance across different classes. Additionally, we propose an adaptive fine coding method for parameter adoption prior to satellite transmission, effectively reducing the delay caused by satellites and ground-specific environmental variations. Experimental results demonstrate that the DEDFL method offers better accuracy and communication efficiency than other baseline algorithms.

This paper investigates adaptive transmission strategies in embodied AI-enhanced vehicular networks by integrating vision language models (VLMs) for semantic information extraction and deep reinforcement learning (DRL) for decision-making. The proposed framework aims to optimize both data transmission efficiency and decision accuracy by formulating an optimization problem that incorporates the Weber-Fechner law, serving as a metric for balancing bandwidth utilization and quality of experience (QoE). Specifically, we employ the large language and vision assistant (LLAVA) model to extract critical semantic information from raw image data captured by embodied AI agents (i.e., vehicles), reducing transmission data size by approximately more than 90% while retaining essential content for vehicular communication and decision-making. In the dynamic vehicular environment, we employ a generalized advantage estimation-based proximal policy optimization (GAE-PPO) method to stabilize decision-making under uncertainty. Simulation results show that attention maps from LLAVA highlight the model's focus on relevant image regions, enhancing semantic representation accuracy. Additionally, our proposed transmission strategy improves QoE by up to 36% compared to DDPG and accelerates convergence by reducing required steps by up to 47% compared to pure PPO. Further analysis indicates that adapting semantic symbol length provides an effective trade-off between transmission quality and bandwidth, achieving up to a 61.4% improvement in QoE when scaling from 4 to 8 vehicles.

The low-altitude economy (LAE), as a new economic paradigm, plays an indispensable role in cargo transportation, healthcare, infrastructure inspection, and especially post-disaster communications. Specifically, unmanned aerial vehicles (UAVs), as one of the core technologies of the LAE, can be deployed to provide communication coverage, facilitate data collection, and relay data for trapped users, thereby significantly enhancing the efficiency of post-disaster response efforts. However, conventional UAV self-organizing networks exhibit low reliability in long-range cases due to their limited onboard energy and transmit ability. Therefore, in this paper, we design an efficient and robust UAV-swarm enabled collaborative self-organizing network to facilitate post-disaster communications. Specifically, a ground device transmits data to UAV swarms, which then use collaborative beamforming (CB) technique to form virtual antenna arrays and relay the data to a remote access point (AP) efficiently. Then, we formulate a rescue-oriented post-disaster transmission rate maximization optimization problem (RPTRMOP), aimed at maximizing the transmission rate of the whole network. Given the challenges of solving the formulated RPTRMOP by using traditional algorithms, we propose a two-stage optimization approach to address it.In the first stage, the optimal multi-path traffic routing and the theoretical upper bound on the transmission rate of the network are derived.In the second stage, we transform the formulated RPTRMOP into a variant named V-RPTRMOP based on the obtained optimal multi-path traffic routing, aimed at rendering the actual transmission rate closely approaches its theoretical upper bound by optimizing the excitation current weight and the placement of each participating UAV via a diffusion model-enabled particle swarm optimization (DM-PSO) algorithm. Simulation results show the effectiveness of the proposed two-stage optimization approach in improving the transmission rate of the constructed network, which demonstrates the great potential for post-disaster communications. Moreover, the robustness of the constructed network is also validated via evaluating the impact of three unexpected situations on the system transmission rate.

Embodied Artificial Intelligence (AI) bridges the cyberspace and the physical space, driving advancements in autonomous systems like theVehicularEmbodiedAINETwork (VEANET). VEANET integrates advanced AI capabilities into vehicular systems to enhance autonomous operations and decision-making. Embodied agents, such as Autonomous Vehicles (AVs), are autonomous entities that can perceive their environment and take actions to achieve specific goals, actively interacting with the physical world. Embodied Agent Twins (EATs) are digital models of these embodied agents, with various Embodied Agent AI Twins (EAATs) for intelligent applications in cyberspace. In VEANETs, EAATs act as in-vehicle AI assistants to perform diverse tasks supporting autonomous driving using generative AI models. Due to limited onboard computational resources, AVs offload EAATs to nearby RoadSide Units (RSUs). However, the mobility of AVs and limited RSU coverage necessitates dynamic migrations of EAATs, posing challenges in selecting suitable RSUs under information asymmetry. To address this, we construct a multi-dimensional contract theoretical model between AVs and alternative RSUs. Considering that AVs may exhibit irrational behavior, we utilize prospect theory instead of expected utility theory to model the actual utilities of AVs. Finally, we employ a Generative Diffusion Model (GDM)-based algorithm to identify the optimal contract designs, thus enhancing the efficiency of EAAT migrations. Numerical results demonstrate the superior efficiency of the proposed GDM-based scheme in facilitating EAAT migrations compared with traditional deep reinforcement learning methods.

Quantum federated learning (QFL) is an emerging interdisciplinary field that merges the principles of quantum computing (QC) and federated learning (FL), with the goal of leveraging quantum technologies to enhance privacy, security, and efficiency in the learning process. Currently, there is no comprehensive survey for this interdisciplinary field. This review offers a thorough, holistic examination of QFL. We aim to provide a comprehensive understanding of the principles, techniques, and emerging applications of QFL. We discuss the current state of research in this rapidly evolving field, identify challenges and opportunities associated with integrating these technologies, and outline future directions and open research questions. We propose a unique taxonomy of QFL techniques, categorized according to their characteristics and the quantum techniques employed. As the field of QFL continues to progress, we can anticipate further breakthroughs and applications across various industries, driving innovation and addressing challenges related to data privacy, security, and resource optimization. This review serves as a first-of-its-kind comprehensive guide for researchers and practitioners interested in understanding and advancing the field of QFL.