Decentralized federated learning (DFL) enables collaborative training through peer-to-peer (P2P) communication, removing reliance on a central coordinator and thereby improving fault tolerance and scalability. In practical DFL deployments, clients differ substantially in data distributions, computational resources, and network bandwidth. Consequently, enforcing a single model architecture across all clients is often infeasible or inefficient, motivating model-heterogeneous DFL. Prior heterogeneous approaches typically exchange distilled knowledge (e.g., logits, soft labels, or class prototypes) rather than model weights; however, under label-distribution skew they often improve performance primarily on locally observed (seen) classes and generalize poorly to locally missing (unseen) classes. We propose ProtoGenesis, a model-heterogeneous DFL framework that improves clients' recognition of unseen classes by combining (i) a semantic-preserving autoencoder trained on public data to support privacy-oriented sample reconstruction from compact latent embeddings and (ii) prototype-based regularization to stabilize representation learning. Clients proactively request lowdimensional embeddings and prototype statistics for selected classes from neighboring peers, reconstruct class-consistent samples locally, and augment training without exchanging raw data or full model parameters. We evaluate ProtoGenesis on image and text classification tasks using CIFAR-10, CIFAR-100, and DBpedia under heterogeneous model-mixing and non-IID settings. ProtoGenesis achieves comparable accuracy on seen classes while improving accuracy on unseen classes form near 0% to up to 70%. Privacy analysis shows that sensitive information cannot be reconstructed from shared embeddings. Moreover, ProtoGenesis reduces communication overhead by about 1500 × and demonstrates low inference and communication latency on a real-world Jetson-based DFL system.

To advance the development of maritime intelligent transportation systems (MITS), underwater wireless sensor networks (UWSNs), composed of numerous sensor nodes, have been widely deployed for underwater information perception. However, UWSNs face critical challenges in achieving cost-effective and timely data collection due to their large-scale deployment and stringent data timeliness requirements. To address this challenge, this paper proposes an efficient data collection scheme for UWSNs through the collaboration between uncrewed surface vehicles (USVs) and autonomous underwater vehicles (AUVs). Specifically, we first introduce a cooperative framework where AUVs select appropriate USVs to form USV-AUV clusters. Within each cluster, AUVs are responsible for sensing data collection, while USVs act as relay nodes, moving toward the destination (e.g., data center). We then devise an evolutionary game-theoretic cluster forming mechanism, deriving evolutionarily stable strategies (ESS) through replicator dynamics analysis, which guarantees a provable Nash equilibrium. Next, we present a hierarchical optimization method that models the interaction between UWSNs and the cluster as a two-agent Markov decision process, where a dual-agent Q-learning algorithm is designed to jointly optimize the decisions of both entities. Finally, extensive simulations demonstrate that the proposed scheme outperforms conventional methods in improving the efficiency of sensing data collection for UWSNs.

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.

Generative artificial intelligence (GAI), e.g., diffusion model is recognized as a promising paradigm for enhancing intelligent transportation systems in vehicular networks. However, the existing implementation of GAI in vehicular networks is limited due to the massive data requirements of GAI and the considerable resources for model training, particularly in distributed vehicular network environments. Federated learning (FL) offers a promising solution by enabling distributed collaborative training for GAI. Therefore, in this paper we present an FL-empowered diffusion model training scheme for vehicular networks. Specifically, first, a novel utility evaluation model based on local model training accuracy is designed to assess the contribution of each vehicle's local model. The interactions between the edge computing servers and vehicles are modeled using a Stackelberg game, while a non-cooperative game determines the optimal strategy among vehicles. To account for the heterogeneity of vehicles and the uncertainty of associated risks, we incorporate prospect theory (PT) to represent subjective utility. Afterward, a backward induction mechanism is devised to determine the Stackelberg equilibrium for deriving the optimal decisions of edge computing servers and vehicles. Finally, simulations are conducted to illustrate that the proposed scheme significantly improves the sum utility rate in comparison to other baseline schemes.

The swift advancement of Location-Based Services (LBSs) raises the danger of trajectory privacy being breached, since the location semantic tags can easily disclose users' sensitive information. Additionally, attackers can exploit temporal correlations to infer sensitive personal information. This paper formulates a personalized semantic trajectory privacy protection framework designed to protect locations with varying sensitivities on the trajectory from the attacker with temporal correlation information. We model the trajectory privacy protection problem as a Markov Decision Process (MDP) and introduce the Reinforcement Learning (RL) technique to dynamically adjust the privacy parameters. 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. Simulation results indicate that the TD3-based personalized semantic trajectory privacy protection mechanism effectively balances the Quality of Service and semantic trajectory privacy while realizing personalized trajectory privacy protection.

With the rapid advancement of the internet of vehicles (IoVs), new types of vehicle applications are emerging continuously. These applications impose increasingly stringent requirements on delay and quality of service standards, which are difficult to meet for vehicle terminals with limited resources. Meanwhile, in the complex computing task system of vehicles, there exists a close correlation between task priorities and computing tasks. As a core technology of space-ground integrated networks, low earth orbit (LEO) satellite communication integrated with vehicle networking can ensure high-efficiency and reliable real-time data transmission. However, additional delay and energy consumption are incurred during the communication between vehicle terminals and satellites. Introducing edge computing into satellite-assisted vehicular networking can satisfy the computing demands of vehicle terminals and reduce the processing delay of vehicle applications, with computing offloading being the key technology. We focus on the LEO satellite assisted vehicular edge computing network. Considering the varying sensitivities of different vehicle tasks to delay and energy consumption, it precisely sets task priorities and proposes a task-priority scheduling scheme. With the objective of minimizing the average delay under constraints of energy consumption, the problem is modeled as a markov decision process (MDP) and addressed by employing the proximal policy optimization (PPO) algorithm within the framework of deep reinforcement learning (DRL). Simulation results demonstrate that the proposed computational offloading algorithm can effectively decrease the system’s average delay, outperforming other benchmark testing methods significantly.

In recent years, with the rapid development of the Internet of Vehicles (IoV) and the widespread application of integrated sensing and communication (ISAC) in the IoV, the integrated sensing and computation offloading in vehicular edge networks has attracted widespread attention from academia and industry. Due to the generation of a large number of latency-sensitive tasks from vehicles’ real-time sensing of road conditions, coupled with the rise of other computing-intensive vehicle applications, the current computing capabilities of the onboard devices cannot meet the diverse demands of vehicular users. Therefore, it is necessary to combine the computing resources around the vehicle to complete computing tasks. With the goal of maximizing the difference between gain and consumption, this article studies the integrated sensing and computation offloading involving roadside units (RSUs) and vehicle platoon in vehicular edge networks. Specifically, we first consider that mobile vehicles can simultaneously offload computing tasks to the RSU and the vehicle platoon via nonorthogonal multiple access (NOMA) technology, and construct a multiobjective optimization problem with the goal of maximizing the utility of the three parties. Then, we construct a game model among the ISAC vehicle, the RSU, and the vehicle platoon based on the Stackelberg game. By seeking the equilibrium of the game, the optimal offloading and pricing strategy are derived, while the utility of the three parties is maximized. Finally, the simulation results show that the proposed scheme is superior to other traditional schemes, and each party in the game obtains its optimal strategy.

Federated learning (FL) encounters slow convergence due to data heterogeneity issues. Recently, generative artificial intelligence (AI) has showcased remarkable capabilities in synthesizing realistic data. To effectively address the challenges of nonindependent and identically distributed (non-IID) data, this article introduces a collaborative AI training framework that leverages generative AI to enhance the learning performance of FL. In this framework, heterogeneous edge devices (HEDs) identify specific data categories lacking in their local data sets and acquire these data from generative AI providers (GAPs). This strategy aims to improve the convergence rate of FL. However, HEDs and GAPs may be reluctant to contribute their resources to FL training due to self-interest. Therefore, an incentive mechanism is necessary to encourage their participation. We propose a reverse auction model to facilitate data transactions among FL training buyers, GAPs, and HEDs within the FL training buyer’s budget. It focuses on determining winners and devising payment rules to maximize the FL training buyer’s utility. This involves solving a 0-1 programming problem with two sellers (GAPs and HEDs). To tackle this, we use joint bidding and virtual seller pairs for analysis. We demonstrate that our method ensures truthfulness, individual rationality, and computational efficiency. Furthermore, we employ a one-side matching mechanism to approximate the optimal solution. We further investigate a strategy to analyze and allocate data based on variance, aiming to minimize non-IID issues in local data. Simulation results demonstrate that our proposed matching mechanism can effectively improve the computational efficiency, with the test accuracy differing from the theoretical optimum by only about 0.7%, and our mechanism can outperform the other greedy algorithms. Additionally, our data allocation strategy enhances the test accuracy by approximately 7% compared to existing methods.

Low earth orbit (LEO) constellation integrated maritime networks have recently attracted much interest due to the rapid development of maritime applications and services. LEO satellites have the advantages of wide coverage to provide seamless connection for maritime wireless devices. However, due to the limited battery and computing capacity of unmanned aerial vehicles (UAVs) for ocean information perception and processing, the computing-intensive and delay-sensitive oceanic data suffer from long latency and high energy consumption, which degrades the efficiency of maritime services. In this paper, to enhance the perception and offloading endurance of UAVs in maritime networks, we propose an energy efficient multi-access edge computing scheme for heterogeneous satellite-maritime networks, with the objective of minimizing the cumulative transmitted energy for UAVs. Specifically, we first present a heterogeneous satellite-maritime network framework in which LEO satellites and unmanned surface vehicles (USVs) equipped with edge servers can process workloads simultaneously. Next, considering the limited battery supply of UAVs, we propose a hybrid harvesting-and-offloading scheme for resource allocation, where UAVs first harvest energy from solar power and radio frequency power from USV, and then UAVs determine the offloading strategy for task processing. Moreover, a joint optimization problem is formulated to optimize the offloading decision, the time scheduling, and the transmitting power. We also exploit a vertical architecture to solve the formulated problem. Regarding each decomposed sub-problem, we propose efficient algorithms to derive the corresponding solutions. Finally, we provide numerical results to validate the performance of our proposed algorithms in comparison with several benchmark algorithms.

With the development of new generation communication technologies, the future maritime information networks pave the way to promote the exploration of ocean resources. Moreover, the underwater data center (UDC) is considered to be a significant data storage and computing unit in future maritime networks for providing ocean services. However, the current deployment of UDC faces the critical issues, i.e., the long-distance underwater transmission is unreliable and the energy consumption and resources of underwater transmission are overloaded. To address the two critical issues of unreliable data transmission and high resource overheads, in this paper, we present a hybrid semantic data transmission architecture in air-ocean integrated networks, which can perceive the sea surface data accurately and transmit it to the UDC for processing. Specifically, in surface layer, uncrewed aerial vehicles (UAVs) perceive ocean environment and send data to the buoy via non-orthogonal multiple-access (NOMA) transmission to improve the channel utilization. In underwater layer, the buoy sends the collected data to UDC via semantic transmission, while the semantic fidelity metric is utilized to improve the transmission efficiency. A resource allocation problem for energy minimization is formulated to jointly optimize the semantic scaling factor, the NOMA decoding order, the communication and computing resource allocations. We exploit a decomposition approach to transform the problem into two sub-problems, where the optimal resource allocations are obtained by proposing efficient algorithms. Finally, we provide simulations to verify the effectiveness and efficiency of our proposed scheme. The results demonstrate that our proposal has the advantages of lower energy consumption compared to several baseline schemes.

Machine learning models can support decision-making in mobile terminals (MTs) deployments, but their training generally requires massive datasets and abundant computation resources. This is challenging in practice due to the resource constraints of many MTs. To address this issue, data-parallel distributed learning can be conducted by offloading computation tasks from MTs to the edge-layer nodes. To facilitate the establishment of trust, one can leverage trust management, say to use trust values derived from local model quality and evaluations by other nodes as access criteria. Nonetheless, security and performance considerations remain unsolved. In this paper, we propose a blockchain-assisted dynamic trust management scheme for distributed learning, which comprises nodes attributes registration, trust calculation, information saving, and block writing. The proof of stake (PoS) consensus mechanism is leveraged to enable efficient consensus among the nodes using trust values as stakes. The incentive mechanism and corresponding dynamic optimization are then proposed to further improve system performance and security. The reinforcement-learning approach is leveraged to provide the optimal strategy for nodes’ local iterations and selection. Simulations and security analysis demonstrate that our proposed scheme can achieve an optimal trade-off between efficiency and quality of distributed learning while maintaining system security.

The rise of artificial intelligence of things (AIoT) has enabled AI-powered services within wireless networks, relying on well-trained machine learning (ML) models. Distributed learning, such as federated learning (FL), allows smart devices (SDs) to collaborate on model training without sharing raw data, but privacy protection is still necessary to prevent potential information leakage from evolving attacks. Additionally, training efficiency is hampered by limited resources and selfishness of SDs. This paper considers a layered distributed learning scenario using a double-layer auction approach, where model users act as buyers, SDs act as data owners contributing their datasets, and edge layer nodes (ELNs) serve as model trainers providing computing resources. The differential privacy (DP) mechanism is utilized to add Gaussian noise to the trained models by the ELNs. Then, we formulate a joint optimization problem to optimize task assignment, data owners' sensing durations, and model trainers' local iterations and privacy budgets, aiming to maximize the utility of all participants while ensuring cost-effective and privacy-preserving distributed learning. We decompose the formulated problem into four sub-problems and design a layered algorithm to solve them and derive collaboration strategies. Simulation results validate the algorithm's performance and demonstrate the advantages of our proposed approach compared to benchmark schemes.

The 6G empowered Internet of vehicles paves the way to autonomous driving era, where the ultra-low latency communication and ultra-reliable connections promote the quality of service (QoS) for vehicle users. However, the high data traffic load and communication resource constraint pose a heavy burden to autonomous driving. This paper proposes a secrecy oriented slicing resource allocation scheme in 6G green vehicular networks. We consider that cellular vehicular user (CUE) and vehicular user equipment (VUE) and eavesdropper coexist in the networks, where VUE can reuse the resource block non-orthogonally with CUE, and the eavesdropper may overhear the data transmission of CUE and VUE. To meet the QoS and green communication requirements, we formulate a joint optimization for energy-efficient resource allocation subject to the data rate and secrecy capacity. Despite the non-convex of the formulated problem, we propose corresponding algorithms to derive the optimal resource allocation strategies. Simulation performance validate the effectiveness of our proposal in comparison with benchmark algorithms.

Parameter-efficient fine-tuning (PEFT) on pre-trained models is a new paradigm for model training, where the majority parameters of a pre-trained model are frozen, left only a small number of unfrozen (or additional) parameters to be tuned. PEFT demonstrates its effectiveness in fitting the downstream tasks, while introducing a new surface for backdoor attacks. In this paper, we design a novel backdoor attack towards the Vision Transformer (ViT) PEFT, called Bad-Tuning. To mislead the target pre-trained model, Bad-Tuning first purposefully tailors the trigger for the frozen portion of the model, and then backdoors the unfrozen part by injecting the trigger into fine-tuning samples of PEFT. The main challenges are two-fold. First, backdooring PEFT should be highly efficient with a few backdoored samples. Second, the trigger should be hardly noticed by human beings as well as backdoor scanners. To deal with the challenges, Bad-Tuning optimizes the trigger by learning CLS sequences which represent rich deep semantics of samples, and introduces color loss to evaluate the invisibility of triggers. Extensive experiments on different datasets demonstrate the effectiveness, efficiency and invisibility of Bad-Tuning under both white-box and gray-box scenarios. Bad-Tuning achieves an average attack success rate (ASR) of over 99.9% even only 0.1% backdoored samples are injected. Moreover, Bad-Tuning outperforms the SOTA backdoor attacks on both ASR and invisibility (SSIM).

Federated learning (FL) collaboratively trains global models while preserving private data locally, making it an ideal privacy-preserving learning technique. However, recent studies have shown that FL poses risks of security attacks and privacy leaks during model parameter transfer. Existing research suggests that backdoor attacks cannot assist with membership inference attacks in machine learning. This paper proposes a joint attack of backdoor injection and membership inference in FL, M-Door, which can connect two independent work lines to ensure the security and privacy of FL. In M-Door, an attacker hidden within the client can not only perform backdoor attacks on the global model, but also perform membership inference attacks on the global model by analyzing the transmitted model parameters. This attack method can improve the success rate of backdoor attacks, and simultaneously increase the success rate of membership inference attacks. We conduct extensive experiments on three image classification tasks to evaluate the effectiveness of M-Door. Compared with the other two attack methods, the experimental results show that M-Door exhibits significant advantages in backdoor and membership inference attacks under both IID and Non-IID data settings.

Virtual Reality (VR) paves the way to link Meta-verse and the real world, allowing users to enjoy immersive experiences. However, delivering high-quality full spherical VR service within limited rendering energy is a challenge. Mobile edge computing (MEC) is a promising paradigm to provide rendering computation services to users. It is widely held that the rendering of panoramic video presents a significant impediment in the VR system, with disregard for the importance of the data correlation leading to excessive energy consumption caused by repeated rendering. In this paper, we propose a cooperative rendering scheme in mm Wave-enabled wireless networks with MEC via a coalition formation game, among which we focus on the data correlation of the background environment of VR streams. Specifically, we first devise a multiple MEC servers rendering framework, and we formulate an optimization problem to maximize the system utility, which contains energy savings for MEC servers and users' quality of experience (QoE). Then, considering the overlap of the VR streams requested by users in Metaverse, a coalition formation game is employed to model the cooperations among MEC servers, such that the user's QoE is significantly improved. The simulation experiments show that our proposed algorithm is superior to benchmark algorithms in improving the users' QoE and reducing the total energy consumption of MEC servers.

Federated learning is a mechanism that allows participating clients to train locally with their own data in order to receive rewards, thus avoiding the transfer of data to a central server and protecting users’ privacy. However, some “lazy” clients may adopt the strategy of fabricating false model local updates in an attempt to “free-riding” without actually contributing real data or consuming local computational resources. To address this issue, we propose FLoomChecker, an integrity detection scheme for federated learning training models. The scheme combines the techniques of trusted execution environments and Bloom filters to efficiently identify clients that do not train honestly by committing and proving. We conducted experimental evaluations of FLoomChecker, examining three main aspects: query time, build time, and memory footprint in trusted execution environment (TEE). The experimental results demonstrate the effectiveness of our scheme, and its performance improves as the number of local training rounds increases.

The integration of unmanned aerial vehicles (UAVs) and marine communication networks has been emerging as a promising paradigm to cater for the growing maritime activities, e.g., marine environment monitoring and ocean resource exploration. The increasing growth of marine applications and services poses challenges for processing marine data, while the resources-limited UAVs cannot satisfy the requirements of computing-intensive and energy consumption. In this paper, we consider a marine edge computing scenario with a group of UAVs and ocean beacon stations (OBSs) and propose a multi-UAV aided multi-access edge computing for marine networks from the perspective of system-welfare and energy-efficient design. Specifically, we propose a multi-task multi-access offloading scheme in marine edge computing networks, in which multiple UAVs can process their workloads locally or offload their partial workloads to multiple OBSs for processing. We consider the total utilities for completing all tasks as the system welfare, and measure the difference between the system welfare and energy consumption as the system revenue. A joint optimization problem is formulated by optimizing the OBS selection, the offloading ratio and the transmission duration, with the objective of increasing the system revenue in marine edge computing networks. We exploit a vertical decomposition architecture to solve the formulated non-convex problem via decomposing it into three sub-problems. Regarding each sub-problem, we propose efficient algorithms to derive the optimal solutions. We finally conduct simulations to verify the performance of the proposed algorithms. The results demonstrate that our proposed algorithms can achieve the best performance for improving the system revenue in comparison with several benchmark algorithms.

The proliferation of unmanned aerial vehicles (UAVs) opens up new opportunities for on-demand service provision anywhere and anytime, but also exposes UAVs to a variety of cyber threats. Low/medium interaction honeypots offer a promising lightweight defense for actively protecting mobile Internet of things, particularly UAV networks. While previous research has primarily focused on honeypot system design and attack pattern recognition, the incentive issue for motivating UAVs’ participation (e.g., sharing trapped attack data in honeypots) to collaboratively resist distributed and sophisticated attacks remains unexplored. This paper proposes a novel game-theoretical collaborative defense approach to address optimal, fair, and feasible incentive design, in the presence of network dynamics and UAVs’ multi-dimensional private information (e.g., valid defense data (VDD) volume, communication delay, and UAV cost). Specifically, we first develop a honeypot game between UAVs and the network operator under both partial and complete information asymmetry scenarios. The optimal VDD-reward contract design problem with partial information asymmetry is then solved using a contract-theoretic approach that ensures budget feasibility, truthfulness, fairness, and computational efficiency. In addition, under complete information asymmetry, we devise a distributed reinforcement learning algorithm to dynamically design optimal contracts for distinct types of UAVs in the time-varying UAV network. Extensive simulations demonstrate that the proposed scheme can motivate UAV’s cooperation in VDD sharing and improve defensive effectiveness, compared with conventional schemes.

Integrated sensing, communications and computing (ISCC) system has been emerged as a crucial paradigm for addressing the growing demand of emerging wireless applications that require both ultra-reliable low-latency computing and high-precision sensing. In this paper, we investigate a non-orthogonal multiple access (NOMA)-assisted integrated sensing and two-tier task offloading (ISTTO) system in which the multi-functional access point (AP) provides task offloading services for a group of edge computing users via NOMA while performing sensing towards a target. To balance the utilization of the computing resources across different tiers, the AP can further offload part of the received workloads to a group of cloudlet servers. To investigate this problem, we formulate a joint optimization of the AP’s transmit beamforming, the two-tier dedicated sensing signals, the two-tier computation offloading strategies and the associated allocations of the communication and computing resources, with the objective of minimizing the total energy consumption, while guaranteeing the required sensing performance over the total duration. Although the formulated joint optimization problem is strictly non-convex, we identify the features of its solutions and exploit a decomposition-based framework for solving it. Numerical results validate the accuracy and effectiveness of our proposed algorithm and show the performance advantages of our NOMA-assisted ISTTO scheme. Compared with several benchmark schemes, our NOMA-assisted ISTTO scheme achieves better performances in both sensing and task offloading, while suppressing the interference from undesired directions.

Human pose estimation is a crucial problem in computer vision, and it has numerous applications in diverse fields such as virtual reality, surveillance, human-computer interaction, and action assistance. With the advent of edge computing, it is a promising paradigm to perform real-time artificial intelligence (AI)-assisted action based on pose estimation at the edge. However, task scheduling optimization for human pose estimation in edge computing is a challenging problem, due to the limited computing resources. In this paper, we propose a novel framework for task scheduling optimization in human pose estimation at the edge. Our framework takes computing resources scheduling and task scheduling decision into account, with the objective of maximizing the quality of service (QoS) of the system. We use multiple depth cameras at different locations to build three-dimensional (3D) poses to maintain the accuracy of estimation and to assist in guiding action. We evaluate our proposed framework on a real-world dataset. The results demonstrate its effectiveness in improving system delay and estimation accuracy in comparison with benchmark methods. We also verify the sensitivity of our proposed framework, which can provide insights into optimal parameter settings for different scenarios.

With the rapid growth of marine services and applications for achieving smart oceans, advanced marine communication networks have attracted increasing interests. However, the limited resources constrain the applications in marine communication networks. In this paper, we investigate a two-tier computation offloading scheme for unmanned aerial vehicle (UAV) aided marine communication networks via game theory to improve offloading efficiency. Specifically, these underwater wireless sensors (UWSs) are deployed at the seafloor, which partially offloads their sensed information to unmanned surface vessels (USVs) for assist computing. USV acts as a relay to offload part of its data to UAVs. We formulate three optimization problems to optimize the utility of UWSs, USVs, and UAVs, respectively. To address the formulated problems, we propose efficient algorithms to derive the solutions, which can maximize the utility of each participant. Finally, simulations are conducted to validate the performance of the proposed algorithms, and the results show the efficiency and effectiveness of the proposed algorithms in comparison with the benchmark schemes.

Abstract The sum‐difference coarray (SDCA) is the union of the sum coarray (SCA) and difference coarray (DCA), which has higher degrees‐of‐freedom (DOF) than that of the DCA, resulting in a better direction‐of‐arrival (DOA) estimation performance. However, existing passive sparse arrays require spatial and temporal information to construct SDCA. In this study, a mirrored coprime array (MCA) is designed to implement SDCA using only spatial information. First, the SCA and DCA are recovered from the vectorised covariance matrix via the transform matrix. A Tikhonov regularisation method is proposed to reduce the rank‐deficiency effect of the transform matrix. The SCA has the potential to fill the holes in the DCA by adjusting the mirror position since the mirror determines the virtual sensor locations of the SCA. Then, the closed‐form expressions of the mirror position and virtual array aperture are derived for the hole‐free SDCA. The consecutive lags of the optimised SDCA are much larger than those of the DCA, significantly increasing the DOF. Numerical simulations verify that the MCA outperforms the non‐mirrored one with respect to the DOA estimation accuracy and resolution.

The rapid development of communication and computing techniques enables unmanned aerial vehicles (UAVs) to provide reliable and cost-effective wireless communication and computing services from the air. Compared to the conventional fixed infrastructure, UAVs have attractive attributes, such as high flexibility and operability, and, as a result, on-demand line-of-sight connection links. Therefore, UAV-assisted wireless networks have been envisioned as a promising paradigm to achieve enhanced coverage and connectivity for future wireless communications. Meanwhile, achieving high levels of energy efficiency, sensing, communication, and computing capacities, and security and privacy are critical to the success of UAV-assisted wireless networks. In order to improve the performance of UAV-assisted wireless networks, some frameworks and mechanisms have been developed in the past few years. In this article, we provide a comprehensive survey of these developments. Specifically, we conduct a brief overview for the architecture of UAV-assisted wireless networks from four domains (i.e., framework-related, technology-related, challenge-related, and solution-related) and four aspects (i.e., sensing-related, communication-related, computing-related, and application-related). Then, the integrated sensing, communication, and computing for UAV-assisted wireless networks is introduced, followed by the characteristics and requirements. We also provide the implementation and applications of UAV-assisted wireless networks. Next, we discuss the challenges and the state-of-the-art solutions for UAV-assisted wireless networks. Finally, the advanced technologies for UAV-assisted communication and computing networks are exploited, followed by the potential research directions.

By interacting, synchronizing, and cooperating with its physical counterpart in real time, digital twin (DT) is promised to promote an intelligent, predictive, and optimized modern city. Via interconnecting massive physical entities and their virtual twins with inter-twin and intra-twin communications, the Internet of DTs (IoDT) enables free data exchange, dynamic mission cooperation, and efficient information aggregation for composite insights across vast physical/virtual entities. However, as IoDT incorporates various cutting-edge technologies to spawn the new ecology, severe known/unknown security flaws, and privacy invasions of IoDT hinder its wide deployment. Besides, the intrinsic characteristics of IoDT, such as decentralized structure, information-centric routing, and semantic communications, entail critical challenges for security service provisioning in IoDT. To this end, this article presents an in-depth review of the IoDT with respect to system architecture, enabling technologies, and security/privacy issues. Specifically, we first explore a novel distributed IoDT architecture with cyber–physical interactions and discuss its key characteristics and communication modes. Afterward, we investigate the taxonomy of security and privacy threats in IoDT, discuss the key research challenges, and review the state-of-the-art defense approaches. Finally, we point out the new trends and open research directions related to IoDT.

The explosively increasing development of marine communication networks will improve the quality of service (QoS) of marine applications (e.g., ocean farm and marine tourism), which has attracted much attention from both academia and industrial in recent years. However, real-time data processing for diverse marine tasks (especially those computing-intensive and latency-sensitive tasks) is still challenging due to the limited marine communication and computing resources. Mobile edge computing (MEC) driven by powerful computing capability is envisioned as a promising solution to address the issue for resource-constrained marine services. In this paper, we propose a hybrid offshore and aerial-based multi-access edge computing scheme in marine communication networks to improve the QoS of marine applications. Specifically, we consider a scenario that both offshore base-station and unmanned aerial vehicles (UAVs) are equipped with edge-servers, and the computation workloads of unmanned surface vehicle (USV) can be simultaneously offloaded to offshore base-station and UAVs via multi-access manner. To minimize the latency of completing USV’s workloads and reduce USV’s energy consumption, we formulate a joint optimization problem to optimize the offloading decision, transmission time, and computing-rate allocation, with the objective ofMinimizing theMaximumWorkloadsLatency (MMWL). Exploiting the features of the formulated problem, we present a layered structure approach and decompose it into three subproblems. We propose efficient algorithms to obtain the optimal solutions and validate the optimality of the proposed algorithms. Finally, we provide simulation results and analysis to demonstrate the effectiveness and efficiency of the proposed scheme and algorithms in comparison with benchmark algorithms.

With the increasing exploration of marine resources, various marine wireless devices have been rapidly deployed for different marine applications such as marine navigation, ocean environment monitoring, and seabed resource exploitation. However, due to long transmission delay and low data rate between marine wireless devices and the cloud, it is challenging to satisfy the service requirements of computing-intensive and delay-sensitive tasks. By migrating computing resources from cloud to the near side of ocean, the paradigm of marine edge computing networks, which integrates communication and computation capacities in marine wireless devices, is expected to support a variety of marine tasks (e.g., data collection, monitoring and processing) with low delay and high data rate. However, considering the rationality and selfishness of marine wireless devices and their limited computing-capacity, how to motivate marine wireless devices to conduct task processing becomes an important problem for improving computing efficiency. To address this issue, in this paper, we propose an incentive oriented two-tier task offloading scheme for marine edge computing networks via hybrid Stackelberg-auction game approach, with the objective of improving the offloading efficiency and maximizing marine wireless devices’ utilities. Specifically, for underwater acoustic transmission tier, we exploit multi-access task offloading scheme, in which underwater wireless sensor (UWS) uploads its workloads to an unmanned underwater vehicle (UUV) and a sea surface sink node (SN) via non-orthogonal multiple access (NOMA) transmission. We formulate the utility of each party and model the task offloading process among UWS, UUV and SN as a Stackelberg game to optimize the UWS’s offloading strategy, UUV’s and SN’s price strategies. For radio frequency transmission tier, SN can offload its partial workloads to an unmanned aerial vehicle (UAV) via frequency division multiple access (FDMA) transmission. We provide their utilities and model the offloading process between a SN and a UAV as a double auction game to optimize their bidding strategies. Extensive simulation results are provided to validate the performance of the proposed scheme. Numerical results demonstrate that the proposed algorithms can obtain the optimal solutions and increase the utilities for marine wireless devices.

The proliferation of unmanned aerial vehicles (UAVs) opens up new opportunities for on-demand service provisioning anywhere and anytime, but it also exposes UAVs to various cyber threats. Low/medium-interaction honeypot is regarded as a promising lightweight defense to actively protect mobile Internet of things, especially UAV networks. Existing works primarily focused on honeypot design and attack pattern recognition, the incentive issue for motivating UAVs' participation (e.g., sharing trapped attack data in honeypots) to collaboratively resist distributed and sophisticated attacks is still under-explored. This paper proposes a novel game-based collaborative defense approach to address optimal, fair, and feasible incentive mechanism design, in the pres-ence of network dynamics and UAVs' multi-dimensional private information (e.g., valid defense data (VDD) volume, communication delay, and UAV cost). Specifically, we first develop a honeypot game between UAVs under both partial and complete information asymmetry scenarios. We then devise a contract-theoretic method to solve the optimal VDD-reward contract design problem with partial information asymmetry, while ensuring truthfulness, fair-ness, and computational efficiency. Furthermore, under complete information asymmetry, we devise a reinforcement learning based distributed method to dynamically design optimal contracts for distinct types of UAVs in the fast-changing network. Experimental simulations show that the proposed scheme can motivate UAV's collaboration in VDD sharing and enhance defensive effectiveness, compared with existing solutions.

With the rapid development of Internet of Things (IoTs), various sensors are deployed to collect different physical information. Smart surveillance is one of applications by analyzing the real-time video generated by camera sensors. However, due to the limited computing capability of camera sensors, running video analysis models (e.g., AlexNet and YOLO3) on camera sensors directly consumes a lot of computing time. In addition, transferring video to the remote cloud suffers a long-distance transmission latency. Fortunately, edge computing has been considered as a promising solution for enabling computation-intensive yet latency-sensitive applications at resource-constrained devices. Thanks to edge computing, camera sensors can upload video to different edge servers employed at the edge of networks for processing. Moreover, the lightweight Kubernetes for edge computing, i.e., K3s, enable a fine-grained task division and parallel computing. In this paper, we consider a heterogeneous edge cooperative video analysis, i.e., face recognition, with the objective of minimizing the processing latency. Specifically, we use a Deep Q-Learning network (DQN) to dynamically adjust the size of pieces video allocated to different edge servers connected via wireless networks. In addition, to improve the resource utilization of edge servers and reduce the processing latency, each edge server further divides the received video into multiple segments that are processed by different containers in parallel. To validate the effectiveness of our scheme, we implement a small-scale prototype system and conduct numerous experiments. Experimental results show that our proposed algorithm outperforms the other four schedule schemes by testing on the tasks of face recognition and pose recognition.

With the development of vehicular networks, the vehicle-to-everything (V2X) communication aided emergency warning is envisioned to improve the safety of driving service in intelligent transportation systems (ITS). By considering the delay sensitivity of different vehicles receiving warning information, this paper investigates the V2X communication aided emergency message dissemination. Specifically, according to the distance between the vehicle and the emergency point, we divide the vehicles in the coverage of the roadside unit (RSU) into two groups, namely, the primary priority group and the secondary priority group. Then, we formulate a joint optimization problem for content partition, user grouping and channel allocation to improve the resource utilization and the efficiency of emergency message delivery. The objective is to ensure that all vehicles in the primary priority group can reliably receive the warning messages within a fixed deadline, and meanwhile, the RSU can send as many warning messages as possible to the vehicles in the secondary priority group. Despite the nature of mixed integer and non-linear programming problem, we propose a layered approach to solve the problem. Finally, we conduct simulations to validate the efficiency and effectiveness of the proposed algorithm, compared to some benchmark algorithms.

Unmanned aerial vehicles (UAVs) empowered with artificial intelligence (AI) have become a new paradigm for marine monitoring and disaster rescue. In AI-enabled UAV applications, UAVs generate amounts of computation-intensive tasks (e.g., image recognition, video processing, and path planning, etc.) that cannot be locally executed by UAVs in time. How to offload the computation-intensive tasks of UAVs timely and effectively has become an urgent challenge. Multiple unmanned surface vehicles (USVs) integrated into a USV fleet is appealingly advocated to provide abundant computation resources for computation tasks. In this paper, we propose a collaborative computation offloading scheme with UAVs and USV fleets in maritime communication networks. Specifically, we first propose a collaborative computation offloading framework, where UAVs act as the requesters of computation offloading, and USV fleets are the assistants. Then, to minimize the overall execution time of computation tasks, UAVs determine the optimal ratio of compu-tation tasks offloaded to USV fleets in the worst case. Afterwards, the first sealed reverse auction with reserve price is utilized to incentivize USV fleets to assist in executing computation tasks of UAVs, where the reserve price guarantees the satisfied benefits of UAVs. Simulation results demonstrate that the proposed scheme reduces the overall execution time and improves the expected revenue of the USV fleet as compared to conventional schemes.

Digital twin (DT), which integrates physical networks and digital space by using advanced technologies of sensing, communication and computation, has been envisioned as a promising paradigm for improving the quality of service in physical systems. In this paper, we propose a federated learning (FL)-enabled DT system consisting of the physical layer and DT layer. With FL, all wireless devices (WDs) can collaborate to update a universal DT model, after the DT server cluster (DSC) aggregates all the local models sent by the WDs with non-orthogonal multiple access (NOMA). Moreover, an action model based on the DT system is also updated to optimize the operations of WDs. To increase the energy efficiency, we formulate a problem to minimize the cost of the total energy consumption of the system by optimizing the time allocation of local training, uploading the local models, generating the action model as well as broadcasting the action model and DT model. The numerical results validate the effectiveness and efficiency of our proposed algorithm.

As the natural disasters may destroy the ground communication infrastructures for the transportation systems, the communication relief in post-disaster networks is more crucial to reduce risk loss. The growing application of unmanned aerial vehicles (UAVs) holds great potential for disaster communication relief due to its flexibility and functionalities. In this paper, we investigate the channel allocation and data delivery problems for UAV-assisted cooperative transportation communications in post-disaster networks to provide communication and data delivery services for affected users. Specifically, we first introduce the UAV-assisted communication relief system, in which UAVs equipped with the communication and caching functionalities are deployed as the aerial base stations in post-disaster regions. Then, we propose the channel allocation scheme between UAVs and users by taking the interferences into consideration, and obtain the channel allocation strategy to improve the network throughput. Based on the optimal channel allocation strategy, users can deliver their data to UAVs for backup. Next, we propose the data delivery scheme to cope with the pricing problem for UAVs and the data delivery strategy for users to improve the efficiency of data delivery, with the objective of maximizing the utilities of both UAVs and users. The optimal strategy for both UAVs and users are derived according to the analysis of Stackelberg game. Finally, we conduct simulations to evaluate the performance of the proposed channel allocation and data delivery scheme, and the numerical results demonstrate that the proposed scheme can significantly improve the efficiency and effectiveness of channel allocation and data delivery in post-disaster networks, compared with benchmark schemes.

Smart city emerges a promising paradigm for improving operational efficiency of city and comfort of people. With embedded multi-sensors, Unmanned Aerial Vehicles (UAVs) hold great potential for collecting sensing data and providing social services in smart city. However, due to the limited battery lifetime and processing capacities of UAVs, the efficient offloading scheme of UAVs is urgently needed in smart city. Therefore, in this article, a vehicle-assisted computing offloading architecture for UAVs is proposed to improve offloading efficiency by harnessing the moving vehicles in smart city. We first develop an offloading model for UAVs to determine the offloading strategy. Next, to select the optimal vehicles for offloading, we formulate a matching scheme based on the preference lists of UAVs and vehicles to derive the optimal matching between UAVs and vehicles. After that, to improve the offloading efficiency and maximize the utilities of UAVs and vehicles, the transaction process of computing data between UAVs and vehicles is modeled as a bargaining game. Moreover, an offloading algorithm for UAVs and vehicles is proposed to obtain the optimal strategy. Finally, simulations are performed to validate the efficiency of the proposed offloading scheme. The results demonstrate that the proposed offloading scheme can significantly save resource and improve the utilities of UAVs and vehicles.

The increasing development of Internet of Things (IoT) has led to the emergence of Internet of connected vehicles (IoCVs). These vehicles with various functionalities have the potential prospects for improving the quality of experience (QoE) of vehicle users. Moreover, the use of unmanned aerial vehicles (UAVs) in flying networks extends the connectivity and universality of IoT, and these UAVs with caching and communication capacities can support various services. However, due to the heterogeneity of vehicular networks and flying networks, the communication performance and content distribution between UAVs and IoCVs expose new challenges in heterogeneous networks (HetNets). Therefore, in this paper, a novel content distribution mechanism between UAVs and IoCVs is proposed to improve the QoE of vehicle users. Specifically, we first develop a novel content distribution architecture for UAVs and IoCVs in HetNets, where the content is distributed by UAV content providers to IoCVs. Next, we establish an optimization problem of content distribution between UAVs and IoCVs to minimize the transmission delay. In order to stimulate UAVs and IoCVs to join content distribution, the utilities of UAVs and IoCVs are formulated, respectively. Moreover, we design a coalition game between UAVs and IoCVs to determine the optimal strategy of content distribution. Finally, simulation results demonstrate that the proposed mechanism can significantly improve the performance of content distribution compared with the conventional mechanisms.

The scalar sensor array (SSA) is generally assumed insensitive to the polarization of impinging signals, and only diversely polarized arrays, such as the vector (crossed-dipole or tripole) sensor array (VSA), can be used for polarization estimation. However, as shown in this paper, with the mutual coupling effect, the SSA can become partially sensitive to polarization of the impinging signals and therefore can be used for polarization parameter estimation. The polarization sensitivity model of an SSA is first established and then as an example, a dimension-reduction method based on multiple signal classification (MUSIC) is employed to jointly estimate the direction-of-arrival and polarization parameters. Computer simulations based on a planar array of circularly polarized microstrip antennas are provided to demonstrate the performance of the proposed method.

As the ever-increasing capacities of internet of things (IoT), unmanned aerial vehicle (UAV)-assisted IoT becomes a promising paradigm for improving network connectivity, extending the coverage of network and computing offloading. However, due to the limitation of battery lifetime and computing capacities of UAVs, the offloading scheme for UAVs presents a new challenge in IoT. Therefore, in this paper, an energy-efficient edge offloading scheme is proposed to improve the offloading efficiency of UAVs. Firstly, based on the data transmission delay of UAVs and computing delay of edge nodes, the matching scheme is designed to obtain the optimal matching between UAVs and edge nodes. Secondly, the energy-efficient offloading scheme for UAVs and edge nodes is modeled as a bargaining game. Then, the offloading strategy based on incentive algorithm is developed to improve the offloading efficiency. Finally, the simulation results demonstrate that the proposed offloading scheme can significantly promote the effectiveness of offloading compared with the conventional schemes.

The popularization of mobile devices connected to the network promotes the rise and development of the emerging mobile Internet of Things (MIoT). Crowdsensing is a promising mode to perceive data in MIoT, where the collection of sensing data is outsourced to the public crowd carrying mobile devices. However, this crowdsensing mode inevitably makes privacy compromised, due to the workers' sensitive information in the sensing data. As such, how to incentivize workers' participation with privacy preservation becomes a challenge. To tackle this problem, in this article, we propose an auction-based privacy-preserving incentive scheme (APIS) for sensing task allocation in MIoT. Specifically, integrating the idea of software-defined network (SDN), we first present a cloud and edge cooperation-based crowdsensing framework, where the cloud is designed as the controller to collect sensing results from the distributed edge nodes and each edge node outsources sensing tasks to participating workers. To motivate workers' participation, we devise a differential privacy-based auction mechanism, whereby each worker can utilize her privacy budget to control how much privacy can be leaked and decide the sensing precision by the sensing time. Moreover, to maximize the utility of the sensing platform, we design a greed-based algorithm to select the winning workers and determine payments to winners. Finally, we conduct extensive simulations to verify the effectiveness of APIS and demonstrate its superiority.

The unmanned surface vehicles (USVs) have been regarded as a promising paradigm to automatically perform emergency tasks in a dynamic maritime traffic environment. However, the performance of maritime communication between USVs and offshore platforms becomes a critical challenge, and the efficiency of task allocation for USVs in the smart ocean is low. In this article, a novel task allocation scheme for USVs in the smart ocean Internet of Things (IoT) is proposed to improve the efficiency of task allocation. First, the offshore platform is developed to provide maritime communication for USVs in the smart ocean IoT. Second, the network resource allocation process between USVs and offshore platforms is modeled as the second price sealed auction game, where the optimal bidding strategy of USV is derived by the Q-learning to maximize the utilities of USVs and offshore platforms. Third, the task allocation scheme is proposed to improve the number of allocated tasks. Finally, the performance of the proposed scheme is conducted based on extensive simulations. The simulation results show that the proposed scheme can significantly improve the number of allocated tasks compared with the conventional schemes.