Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead. To address these challenges, this paper presents a new FDG framework, dubbed FaST-PT, which facilitates local feature augmentation and efficient unseen domain adaptation in a distributed manner. First, we propose a lightweight Multi-Modal Style Transfer (MST) method to transform image embedding under text supervision, which could expand the training data distribution and mitigate domain shift. We then design a dual-prompt module that decomposes the prompt into global and domain prompts. Specifically, global prompts capture general knowledge from augmented embedding across clients, while domain prompts capture domain-specific knowledge from local data. Besides, Domain-aware Prompt Generation (DPG) is introduced to adaptively generate suitable prompts for each sample, which facilitates unseen domain adaptation through knowledge fusion. Extensive experiments on four cross-domain benchmark datasets, e.g., PACS and DomainNet, demonstrate the superior performance of FaST-PT over SOTA FDG methods such as FedDG-GA and DiPrompt. Ablation studies further validate the effectiveness and efficiency of FaST-PT.

The rapid advancement of large language models (LLMs) has resulted in increasingly sophisticated AI-generated content, posing significant challenges in distinguishing LLM-generated text from human-written language. Existing detection methods, primarily based on lexical heuristics or fine-tuned classifiers, often suffer from limited generalizability and are vulnerable to paraphrasing, adversarial perturbations, and cross-domain shifts. In this work, we propose SentiDetect, a model-agnostic framework for detecting LLM-generated text by analyzing the divergence in sentiment distribution stability. Our method is motivated by the empirical observation that LLM outputs tend to exhibit emotionally consistent patterns, whereas human-written texts display greater emotional variability. To capture this phenomenon, we define two complementary metrics: sentiment distribution consistency and sentiment distribution preservation, which quantify stability under sentiment-altering and semantic-preserving transformations. We evaluate SentiDetect on five diverse domains and a range of advanced LLMs, including Gemini-1.5-Pro, Claude-3, GPT-4-0613, and LLaMa-3.3. Experimental results demonstrate its superiority over state-of-the-art baselines, with over 16% and 11% F1 score improvements on Gemini-1.5-Pro and GPT-4-0613, respectively. Moreover, SentiDetect also shows greater robustness to paraphrasing, adversarial attacks, and text length variations, outperforming existing detectors in challenging scenarios.

Graph Neural Networks (GNNs) with differential privacy have been proposed to preserve graph privacy when nodes represent personal and sensitive information. However, existing methods ignore that nodes with different importance may yield diverse privacy demands, which may lead to over-protecting some nodes and decrease model utility. In this paper, we study the problem of importance-grained privacy, where nodes contain personal data that need to be kept private but are critical for training a GNN. We propose NAP-GNN, a node-importance-grained privacy-preserving GNN algorithm with privacy guarantees based on adaptive differential privacy to safeguard node information. First, we propose a Topology-based Node Importance Estimation (TNIE) method to infer unknown node importance with neighborhood and centrality awareness. Second, an adaptive private aggregation method is proposed to perturb neighborhood aggregation from node-importance-grain. Third, we propose to privately train a graph learning algorithm on perturbed aggregations in an adaptive residual connection mode over multi-layer convolution for node- wise tasks. The theoretical analysis shows that NAP-GNN can guarantee privacy. Empirical experiments over five real-world graph datasets show that NAP-GNN achieves a better trade-off between privacy and accuracy.

Coded distributed machine learning mitigates straggler effects and provides privacy protection by introducing redundancy through coded computing. However, the system remains vulnerable to privacy breaches when the number of honest-but-curious nodes surpasses the designed threshold, or when outsider adversaries eavesdrop on sensitive data. To address these limitations, we propose a privacy-preserving and straggler-resilient distributed learning framework, namely, differential privacy-based Lagrange coded computing (DP-LCC). First, we design a three-layer protection strategy against privacy threats and stragglers by retaining labels at the master, obfuscating features via Lagrange interpolation, and injecting calibrated noise into local computations. Second, we theoretically prove that the aggregated gradient is an unbiased estimator with bounded variance, and derive convergence bounds under both Gaussian and Laplace mechanisms, revealing the trade-off between privacy budgets and model utility. Third, we provide a comprehensive analysis of the system's computational complexity, privacy composition, and heterogeneity to verify the framework's efficiency and adaptability in realistic distributed environments. Extensive experiments on four benchmark datasets validate the theoretical results, demonstrating the robustness of DP-LCC against varying system parameters and heterogeneous environments.

Multimodal Recommendation Systems (MRSs) boost traditional user-item interaction-based methods by incorporating multimodal information. However, existing methods ignore the inherent noise brought by (1) noisy semantic priors in multimodal content, and (2) noisy user interactions in history records, therefore diminishing model performance. To fill this gap, we propose to denoise MRSs by jointly EValuating structure Effectiveness and mitigating Noisy links (EVEN). Firstly, for semantic prior noise in multimodal content, EVEN builds item homogeneous consistency and denoises it by evaluating behavior-driven confidence. Secondly, for noise in user interactions, EVEN updates user feedback by denoising observed interactions following implicit contribution evaluation of high-order representations. Thirdly, EVEN performs cross-modal alignment through self-guided structure learning, reinforcing task-specific inter-modal dependency modeling and cross-modal fusion. Through extensive experiments on three widely-used datasets, EVEN achieves an average improvement of 8.95% and 5.90% in recommendation accuracy compared with LGMRec and FREEDOM, respectively, without extending the total training time.

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the fully-supervised detection head. We argue that the noise in pseudo-labels would interfere with the learning of fully-supervised detection head, leading to significant performance leakage. Issues with noisy labels include:(1) inaccurate boundary localization; (2) undetected short action clips; (3) multiple adjacent segments incorrectly detected as one segment. To target these issues, we introduce a two-stage noisy label learning strategy to harness every potential useful signal in noisy labels. First, we propose a frame-level pseudo-label generation model with a context-aware denoising algorithm to refine the boundaries. Second, we introduce an online-revised teacher-student framework with a missing instance compensation module and an ambiguous instance correction module to solve the short-action-missing and many-to-one problems. Besides, we apply a high-quality pseudo-label mining loss in our online-revised teacher-student framework to add different weights to the noisy labels to train more effectively. Our model outperforms the previous state-of-the-art method in detection accuracy and inference speed greatly upon the THUMOS14 and ActivityNet v1.2 benchmarks.

Using extensive training data from SA-1B, the Segment Anything Model (SAM) has demonstrated exceptional generalization and zero-shot capabilities, attracting widespread attention in areas such as medical image segmentation and remote sensing image segmentation. However, its performance in the field of image manipulation detection remains largely unexplored and unconfirmed. There are two main challenges in applying SAM to image manipulation detection: a) reliance on manual prompts, and b) the difficulty of single-view information in supporting cross-dataset generalization. To address these challenges, we develops a cross-view prompt learning paradigm called IMDPrompter based on SAM. Benefiting from the design of automated prompts, IMDPrompter no longer relies on manual guidance, enabling automated detection and localization. Additionally, we propose components such as Cross-view Feature Perception, Optimal Prompt Selection, and Cross-View Prompt Consistency, which facilitate cross-view perceptual learning and guide SAM to generate accurate masks. Extensive experimental results from five datasets (CASIA, Columbia, Coverage, IMD2020, and NIST16) validate the effectiveness of our proposed method.

Group fairness based on adversarial training has gained significant attention on graph data, which was implemented by masking sensitive attributes to generate fair feature views. However, existing models suffer from training instability due to uncertainty of the generated masks and the trade-off between fairness and utility. In this work, we propose a stable fair Graph Neural Network (SFG) to maintain training stability while preserving accuracy and fairness performance. Specifically, we first theoretically derive a tight upper Lipschitz bound to control the stability of existing adversarial-based models and employ a stochastic projected subgradient algorithm to constrain the bound, which operates in a block-coordinate manner. Additionally, we construct the uncertainty set to train the model, which can prevent unstable training by dropping some overfitting nodes caused by chasing fairness. Extensive experiments conducted on three real-world datasets demonstrate that SFG is stable and outperforms other state-of-the-art adversarial-based methods in terms of both fairness and utility performance. Codes are available at https://github.com/sh-qiangchen/SFG.

Open-vocabulary object detection (OvOD) uses Vision-Language Models (VLMs) to detect arbitrary categories specified by natural language. However, existing methods often struggle with performance instability caused by granularity-induced semantic drift, which arises from misaligned label embeddings across varying levels of specificity. In this paper, we propose GraSecon, a Graph-guided Semantically Consistent representation framework that enhances zero-shot detection robustness without requiring additional training. We construct a hierarchical Fine-grained Semantic Graph enriched with visually grounded attributes from large language models (LLMs). This graph captures hierarchical, sibling and cross-level relations, enabling controlled Laplacian refinement to harmonize the embedding space and improve visual-semantic alignment. To strengthen fine-grained discriminability, we introduce a Key Semantic Node Mining module that identifies and anchors semantically sensitive nodes, ensuring robust feature representation. Furthermore, our Semantic Relevance-Driven Laplacian Propagation adaptively propagates information, promoting coherent and context-aware embedding alignment across granularities. Extensive experiments on the iNatLoc and FSOD datasets demonstrate that GraSecon outperforms prior SOTA methods, achieving average mAP50 improvements of 6.5% and 5.4%. Code is publicly available at: https://github.com/minoslab-csu/GraSecon.

Federated Prompt Tuning (FPT) integrates large pre-trained Vision Transformers (ViT) into Federated Learning (FL) by leveraging Visual Prompt Tuning (VPT), achieving state-of-the-art performance with enhanced efficiency across various visual downstream tasks. However, data heterogeneity, such as feature shift and class imbalance, limits prompts' transferability and robustness in FPT. Existing methods primarily focus on generalized FPT (GFPT) or personalized FPT (PFPT), while only a few methods make initial attempts to integrate both approaches. In this paper, we propose a new FPT framework, dubbed DualFPT, which handles data heterogeneity from both generalized and personalized perspectives. Specifically, DualFPT divides the learnable prompts into global and local prompts to jointly capture general and client-specific information, achieving the harmonization of GFPT and PFPT. The generalization of DualFPT is realized by the Feature Sharing (FS) mechanism, which effectively narrows the distribution gap by allowing clients to securely share a portion of sensitive features. The key feature for improving personalization is the Prompt Composition Scheme (PCS), which weights local prompts with distribution similarity to generate composite prompts, thus achieving automatic distribution adaptation. Extensive experiments under feature shift and class imbalance scenarios demonstrate the superior performance of DualFPT. On DomainNet and CIFAR-100 (D (0.1)), DualFPT surpasses SGPT by 4.35% and 5.89% for generalization along with 7.89% and 9.09% for personalization. Ablation studies further validate the effectiveness, efficiency, and security of DualFPT.

Recent advancements in graph unlearning models have enhanced model utility by preserving the node representation essentially invariant, while using gradient ascent on the forget set to achieve unlearning. However, this approach causes a drastic degradation in model utility during the unlearning process due to the rapid divergence speed of gradient ascent. In this paper, we introduce INPO, an Influence-aware Negative Preference Optimization framework that focuses on slowing the divergence speed and improving the robustness of the model utility to the unlearning process. Specifically, we first analyze that NPO has slower divergence speed and theoretically propose that unlearning high-influence edges can reduce impact of unlearning. We design an influence-aware message function to amplify the influence of unlearned edges and mitigate the tight topological coupling between the forget set and the retain set. The influence of each edge is quickly estimated by a removal-based method. Additionally, we propose a topological entropy loss from the perspective of topology to avoid excessive information loss in the local structure during unlearning. Extensive experiments conducted on five real-world datasets demonstrate that INPO-based model achieves state-of-the-art performance on all forget quality metrics while maintaining the model's utility. Codes are available at https://github.com/sh-qiangchen/INPO.

Edge computing-enabled virtual reality (VR) is increasingly explored in smart healthcare systems due to its potential to deliver immersive, real-time medical services. However, ensuring ultra-low latency and interpretable decision-making in such systems remains a significant challenge. In this paper, we propose an explainable deep reinforcement learning (XDRL)-enhanced VR video streaming framework for immersive healthcare systems to provide smooth and reliable VR services. Specifically, we first model the VR content analysis process at the edge sides and formulate a joint caching, communication, and computing (3C) resource optimization problem to maximize the VR quality of service (QoS) and minimize service latency. To address this complex 3C resource scheduling decision problem, we propose HXRL, a novel implementation of explainable deep reinforcement learning (XDRL), specifically designed to optimize immersive healthcare VR services. Comprehensive experiments show that our HXRL method improves average tile bitrate by 18.3%, cache hit ratio by 24.7%, and reduces system latency by 32.5% compared to baselines on real-world VR healthcare datasets. Moreover, a class activation map (CAM)-based visual analysis is integrated to interpret the learned policies of our model, highlighting the spatial attention of decision-making and enhancing trustworthiness in medical contexts.

With increasing cyber attacks over the Internet, network intrusion detection systems (NIDS) have been an indispensable barrier to protecting network security. Taking advantage of automatically capturing topology connections, recent deep graph learning approaches have achieved remarkable performance in distinguishing different types of malicious flows. However, there remain some critical challenges. 1) previous supervised learning methods rely heavily on abundant and high-quality annotated samples, while label annotation requires abundant time and expert knowledge. 2) Centralized methods require all data to be uploaded to a server for learning behavior patterns, which results in high detection latency and critical privacy leakage. 3) Diverse attack scenarios exhibit highly imbalanced distribution, making it hard to characterize abnormal behaviors. To address these issues, we proposed FeCoGraph, a label-aware federated graph contrastive learning framework for intrusion detection in few-shot scenarios. The line graph is introduced to directly process flow embeddings, which are compatible with diverse GNNs. Furthermore, We formulate a graph contrastive learning task to effectively leverage label information, allowing intra-class embeddings more compact than inter-class embeddings. To improve the scalability of NIDS, we utilize federated learning to cover more attack scenarios while protecting data privacy. Experiment results show that FeCoGraph surpass E-graphSAGE with an average 8.36% accuracy on binary classification and 6.77% accuracy on multiclass classification, demonstrating the efficiency of our approach.

Graph Neural Networks (GNNs) have demonstrated remarkable potential in various downstream tasks by effectively capturing the relational dependencies among nodes in graphs. However, this capability also brings significant privacy risks: when GNNs encode topological information and node features into their output, sensitive information can be inadvertently exposed, leading to severe privacy breaches. Existing privacy-preserving GNNs primarily focus on protecting the existence of individual nodes or edges, overlooking practical scenarios where nodes and edges are often publicly accessible and only specific sensitive attributes require protection, resulting in a lack of consideration for attribute sensitivity and challenges in balancing privacy and utility. In this paper, we study the problem of hiding sensitive information during GNN training and limiting its exposure in the outputs, while better defending against attribute inference attacks (AIAs) and achieving improved performance. To achieve this, we propose an attribute-oriented differentially private graph neural network (AODP-GNN) that enforces attribute-specific privacy guarantees through dynamic privacy budgets and relevance-aware noise injection, optimizing the balance between privacy and utility. Specifically, we design a neighborhood-aware private embedding generation mechanism and a mutual information minimization-based optimization strategy that operate before the deep interactions of feature interaction and model optimization to strengthen defense against AIAs. To enhance the balance between privacy and utility, we further develop a relevance-grained noise adaptation technique that dynamically allocates higher noise to less relevant attributes. Theoretical analysis shows that the AODP-GNN satisfies privacy guarantees. Extensive experiments conducted on four real-world datasets demonstrate that our approach can achieve up to around 10.04% and 9.21% higher accuracy compared to the state-of-the-art centrally differentially private GNN ProGAP and DPDGC, and also shows a higher defense capability against AIAs.

With the increasing size of Internet of Things (IoT) devices, cyber threats to IoT systems have increased. Federated learning (FL) has been implemented in an anomaly-based intrusion detection system (NIDS) to detect malicious traffic in IoT devices and counter the threat. However, current FL-based NIDS mainly focuses on global model performance and lacks personalized performance improvement for local data. To address this issue, we propose a novel personalized federated meta-learning intrusion detection approach (PerFLID), which allows multiple participants to personalize their local detection models for local adaptation. PerFLID shifts the goal of the personalized detection task to training a local model suitable for the client’s specific data, rather than a global model. To meet the real-time requirements of NIDS, PerFLID further refines the client selection strategy by clustering the local gradient similarities to find the nodes that contribute the most to the global model per global round. PerFLID can select the nodes that accelerate the convergence of the model, and we theoretically analyze the improvement in the convergence speed of this strategy over the personalized federated learning algorithm. We experimentally evaluate six existing FL-NIDS approaches on three real network traffic datasets and show that our PerFLID approach outperforms all baselines in detecting local adaptation accuracy by 10.11% over the state-of-the-art scheme, accelerating the convergence speed under various parameter combinations.

Multi-agent perception (MAP) allows autonomous systems to understand complex environments by interpreting data from multiple sources. This paper investigates intermediate collaboration for MAP with a specific focus on exploring "good" properties of collaborative view (i.e., post-collaboration feature) and its underlying relationship to individual views (i.e., pre-collaboration features), which were treated as an opaque procedure by most existing works. We propose a novel framework named CMiMC (Contrastive Mutual Information Maximization for Collaborative Perception) for intermediate collaboration. The core philosophy of CMiMC is to preserve discriminative information of individual views in the collaborative view by maximizing mutual information between pre- and post-collaboration features while enhancing the efficacy of collaborative views by minimizing the loss function of downstream tasks. In particular, we define multi-view mutual information (MVMI) for intermediate collaboration that evaluates correlations between collaborative views and individual views on both global and local scales. We establish CMiMNet based on multi-view contrastive learning to realize estimation and maximization of MVMI, which assists the training of a collaborative encoder for voxel-level feature fusion. We evaluate CMiMC on V2X-Sim 1.0, and it improves the SOTA average precision by 3.08% and 4.44% at 0.5 and 0.7 IoU (Intersection-over-Union) thresholds, respectively. In addition, CMiMC can reduce communication volume to 1/32 while achieving performance comparable to SOTA. Code and Appendix are released at https://github.com/77SWF/CMiMC.

Nowadays, collaborative federated learning (CFL) is developing rapidly in the Internet of Things (IoT), which allows clients to jointly train models without compromising private data. The existing research has studied alone either trust enhancement or privacy preservation issues in CFL. Due to the highly coupled nature of trust and privacy in a collaborative environment, it is worth investigating how to balance appropriate trust and privacy tradeoffs for realizing high-quality CFL. In this paper, we come up with the idea of "trading Trust for Privacy", and propose a novel socially-motivated personalized privacy-preserving federated learning (SP-PFL) framework, which aims to realize social trust-grained privacy protection. First, we design a social trust evaluation method among CFL clients, which is based on topological relation and attribute similarity. Based on the obtained trust value, we then propose a trust-grained privacy budget allocation strategy for SP-PFL, which could further adaptively adjust the differential privacy (DP) noise perturbation. Besides, we provide an analysis of privacy and convergence for our SP-PFL. Finally, we experiment with different models and parameter settings on different datasets. Extensive experimental results show that our method maintains personalized privacy and effectively improves the accuracy by 6.11% on the CNN model and MNIST dataset.

Web 3.0 and Edge computing are inherently compatible, making them an ideal combination for building a secure and efficient distributed service platform to support decentralized applications (DApps). This paper investigates an elastic hybrid computing architecture in Edge Web 3.0, allowing DApp tasks to be executed in a hybrid manner by integrating on-chain and off-chain execution. The principle is to transfer a portion of DApp to an off-chain execution environment, along with an appropriate result verification process, to enhance computing efficiency and reduce blockchain overhead. We formulate a DApp task scheduling problem that jointly optimizes the execution pattern and offloading decision of user tasks. A learning-based DApp task scheduling scheme is designed based on Proximal Policy Optimization (PPO) to minimize the gas cost and service delay of DApps. Particularly, we tailor PPO to handle the hard constraints of service delay, gas consumption, and computing capacity in Edge Web 3.0 by adding regularization terms in the learning objective function. We establish an Edge Web 3.0 testbed based on Goerli, ZkSync, and Ethereum to evaluate the proposed method. The experimental results show that our method outperforms state-of-the-art benchmarks.

Swarm Learning (SL) provides a secure distributed learning environment to edge computing (EC) networks by leveraging blockchain technology for certified participation, encrypted information transmission, and immutable data storage. However, vanilla SL faces scalability limitations due to system-wide model aggregation, which bottlenecks its communication and blockchain efficiency. This paper presents a novel framework called Peer-to-peer Swarm Learning Over consOrtium blOckchain$(\mathbf{PSLO}_{3})$to enhance the scalability of SL over EC networks. PSLO3proposes a peer-to-peer swarm learning (P2P-SL) mechanism that only requires local communications for P2P model aggregation, thereby reducing the communication overhead of vanilla SL for system-wide model aggregation. Furthermore, PSLO3delivers P2P-SL over consortium blockchain and strategically organizes the edge servers into subchains to minimize the overhead of P2P-SL over consortium blockchain. A subchain formation scheme is designed based on graph partitioning by jointly analyzing the topological property of EC networks, message-passing patterns of P2P-SL, and the overhead of cross-/intra-chain interactions. An evaluation environment is built based on the Wecross platform to evaluate the performance of PSLO3. Experimental results demonstrate that PSLO3provides a reduction of 81.1% in communication overhead and a reduction of 26.03% in blockchain cost compared to vanilla swarm learning while demonstrating comparable learning performances.

In recent years, the rapid development of the Industrial Internet of Things (IIoT) has enabled real-time communication and data sharing among devices, significantly enhancing industrial production efficiency and security. Furthermore, the introduction of edge learning allows models to be trained on edge industrial devices. However, with the continuous growth of industrial data, challenges such as resource optimization in edge environments, edge node motivation, and threats from malicious nodes are increasingly posing obstacles to the advancement of edge learning. In this paper, we propose Blockchain and Coded Computing based Secure Edge Learning (BCC-SEL). First, we introduce a coded edge learning framework with Lagrange Coded Computing (LCC) for resource-efficient use of idle nodes during training. Based on the blockchain, we further propose an incentive mechanism to reward and punish the participating training clients. Finally, we guarantee the robustness of the framework using the detection method based on cosine-similarity. We provide theoretical proof that our approach effectively reduces the computational consumption of training nodes. In terms of experiments, our method effectively rewards honest nodes that participate in training and penalizes malicious nodes while guaranteeing accuracy.

Backdoor attacks can mislead deep bug search models by exploring model-sensitive assembly code, which can change alerts to benign results and cause buggy binaries to enter production environments. But assembly instructions have strict constraints and dependencies, and these additional model-sensitive assembly codes destroy semantics and syntax and are easily detected by dynamic analysis or context-based detection. To escape from the dynamic analysis-based detection, we propose a novel latent backdoor attack (LateBA) scheme based on the locality principle of program execution, which only poisons a few of infrequent execution codes, minimizing the effects on the original code logic. In LateBA, a progressive seed mutating strategy is designated to change the American Fuzzy Lop (AFL)-based path search tool to pay more attention to infrequent execution codes. With this strategy, the optimal range to positions in the whole program is determined. Subsequently, triggers are target model-sensitive assembly instructions, and try to minimize the variables that have been called in the context instructions in the trigger. Finally, we employ code semantic feature comparisons to select precise trigger injection positions within these ranges. The selection criteria of the trigger injection position is whether the corresponding code segments in this position have a data dependency relationship with other code segments. We evaluate the performance of LateBA over 7 deep bug search tasks. The results demonstrate the attack success rate of the proposed LateBA is considerable and competitive against the baselines.

By leveraging multi-view inputs to synthesize novel-view images, Neural Radiance Fields (NeRF) have emerged as a prominent technique in the realm of 3D object reconstruction. However, the input images of NeRF transmitted through high-interference wireless environment (HIWE) leads to negatively impact the accuracy of 3D reconstruction, thereby limiting its scalability. Fortunately, semantic communication has been proved a effective method to solve the above problem. In this paper, we propose a novel NeRF based 3D semantic communication (NeRF-3DSC) system, which offers robust 3D reconstruction in HIWE. Within NeRF-3DSC, semantic encoder and decoder are employed to extract and recover core semantic features of task-specific specific object (TSO) from the collected images, channel encoder and decoder ensure robust transmission of compressed semantic information in HIWE, lightweight renderer based on NeRF is employed for fast and efficient 3D reconstruction. Moreover, a semantic control unit (SCU) is introduced to guide above components, thereby enhancing the efficiency of reconstruction. Demonstrative experiments demonstrate that the proposed NeRF-3DSC enables robust object reconstruction in HIWE, surpassing the performance of state-of-the-art (SOTA) methods in terms of reconstruction quality.

Differential-Private Graph Neural Networks (DP-GNNs) have generated remarkable research results, enabling them to effectively tackle the privacy leakage problem in graph learning. However, most DP-GNNs do not consider the temporal-dimensional scenarios. In tasks involving spatiotemporal graph training, such as wireless social networks analysis, the sensitive interactive information in each time graph should be protected. Therefore, we propose spatio-temporal dynamic graph learning with enhanced local differential privacy (LDP-STG). First, we design a weighted graph perturbation encoder based on the Bernoulli distribution and Laplace mechanism, which protects the structures of weighted graphs in time series under edge-level local differential privacy. Second, we employ an attention mechanism to learn dynamic graph node embedding from spatial and temporal dimensions. The theoretical analysis proves that our LDP-STG realizes differential privacy guarantees. We conduct experiments mainly on two communication datasets (i.e., Enron and UCI), which shows that our LDP-STG can achieve better privacy utility tradeoffs compared with traditional mechanisms in terms of snatiotemnoral dimensions.

The Internet of Vehicles (IoV) connects a massive amount of smart vehicles for inter/intra-vehicle information sharing. Data privacy issues, such as privacy leakage and privacy cost are the key challenges that hinder vehicle operators from sharing their data safely. Traditional privacy-preserving techniques, including Federated Learning (FL) and Differential Privacy (DP) techniques, can protect data privacy and security, but the high privacy cost severely limits learning performance. In addition, the IoV services place high demands on low communication latency, which can be obtained by reducing the communication bits, but it also limits the learning performance. Thus, how to solve the communication-privacy-accuracy tradeoffs to achieve low latency, high privacy preservation and model performance has been a complicated issue in IoV. In this paper, a privacy-enhancement differentially private federated learning framework (FedSDP) is proposed based on the shuffle model to ensure secure and efficient data sharing under the constraint of low latency in IoV. In our proposed framework, four privacy enhancement methods are proposed, including data subsampling, vehicle sampling, shuffle model and dummy points, to amplify the privacy and obtain higher learning performance. Then, a Top-K sparsification mechanism of the vehicle training process is proposed to reduce communication bits. Finally, the experimental results indicate that our approach can reduce the communication latency by 31.66%, enhance the privacy ϵc by 30.77% and improve the test accuracy by 48.56%, compared with the traditional SDP mechanism.

To reduce attack risks in Internet of Things (IoT), many security vendors conduct software security analysis on IoT devices all the time. However, how to build an ultralow-latency threat alerting strategy using software vulnerability information still faces challenges. First, existing terminal threat detection methods for IoT systems relying on Indicators of Compromise (IoC) threat intelligence can only cover limited software vulnerabilities so the alert validity rate is still very low. Second, most users lack security knowledge and cannot proactively distinguish high-risk vulnerabilities, resulting in untimely reporting. In this article, a novel hierarchical software execution state representation (HSESR) scheme is proposed for ultralow latency threat alerting over IoT systems based on Beyond 5G. In HSESR, function call graphs are recorded and delivered to edge servers for swiftly identifying suspicious threat behaviors based on deep graph representation, while corresponding instruction sequences are delivered to the cloud data center for further matching the vulnerability information via recurrent semantic representation. To improve the effectiveness of HSESR, the graph representation is also actively encapsulated into the corresponding semantic representation, together acting as an implicit threat behavior signature, which is essential to associate with a security patch. Moreover, to accelerate the detection of suspicious behaviors, we also propose a deep reinforcement learning-based graph searching (DRL-GS) strategy to crop the huge function call graph of the entire software to timely report high-risk threat behaviors with minimized resource consumption. By instancing 1-day attacks on a simulated beyond 5G IoT system, the performance of HSESR is trustfully competitive against existing baselines, and the efficiency of threat detection was increased by 21.63%.

In the era of 5G and beyond, the increasing complexity of wireless networks necessitates innovative frameworks for efficient management and deployment. Digital twins (DTs), embodying real-time monitoring, predictive configurations, and enhanced decision-making capabilities, stand out as a promising solution in this context. Within a time-series data-driven framework that effectively maps wireless networks into digital counterparts, encapsulated by integrated vertical and horizontal twinning phases, this study investigates the security challenges in distributed network DT (NDT) systems, which potentially undermine the reliability of subsequent network applications, such as wireless traffic forecasting. Specifically, we consider a minimal-knowledge scenario for all attackers, in that they do not have access to network data and other specialized knowledge, yet can interact with previous iterations of server-level models. In this context, we spotlight a novel fake traffic injection attack designed to compromise a distributed NDT system for wireless traffic prediction. In response, we then propose a defense mechanism, termed global-local inconsistency detection (GLID), to counteract various model poisoning threats. GLID strategically removes abnormal model parameters that deviate beyond a particular percentile range, thereby fortifying the security of network twinning process. Through extensive experiments on real-world wireless traffic data sets, our experimental evaluations show that both our attack and defense strategies significantly outperform existing baselines, highlighting the importance of security measures in the design and implementation of DTs for 5G and beyond network systems.

The convergence of blockchain and deep learning (DL) drives the intelligence of the Internet of Things (IoT) with security guarantees. However, the soaring resource consumption resulting from blockchain mining and DL model training has overwhelmed the extremely resource-constrained IoT. In this article, we first build a blockchain and DL-empowered cloud–edge orchestrated framework for an extremely resource-constrained IoT environment. To solve the resource bottleneck of this framework, we then propose a Zero-knowledge Proof of Learning (ZPoL) consensus approach to channel the meaningless Proof of Work (PoW) mining energy waste to valuable DL model training, while protecting the DL model privacy. Besides, to encourage resource-constrained IoT devices to perform meaningful DL model mining in our ZPoL consensus, we design a model quality-aware incentive mechanism based on a two-stage Stackelberg game. Moreover, we conduct extensive simulations and experiments to evaluate our proposed ZPoL-based framework. The numerical simulation illustrates that our proposed incentive mechanism could motivate IoT devices to actively join in DL model mining. Compared with the existing blockchain and DL-enabled IoT system, experimental results demonstrate that our proposed ZPoL-based framework could significantly reduce the communication, computation, and storage cost, which is more applicable to a resource-constrained IoT environment.

The susceptibility of millimeter-wave (mmWave) links to blockages poses challenges for maintaining consistent high-rate performance. By predicting link quality in advance at specific locations or times of interest, proactive resource allocation techniques, such as link-quality-aware scheduling, can be employed to optimize the utilization of network resources. In this paper, we introduce a map-driven link quality prediction framework that divides the problem into long-term and short-term link quality predictions to cater to the needs of mobile computing. The first stage aims to predict a long-term radio map considering static network characteristics. We propose to separate LoS and NLoS scenarios, and build an analytical model and a regression-based approach to construct a complete link quality map in the spatial domain. Next, short-term link quality prediction is explored to anticipate future variations in link quality through a spatial-temporal attention-based prediction framework. The essence of this approach lies in capturing the spatial correlation and temporal dependency of mmWave wireless characteristics, followed by an attention mechanism to complement the dynamic link quality prediction task. On top of that, we also design a regional training mechanism with a weighted loss function to address the classical data imbalance problem of map-driven prediction. Extensive experimental and simulation results show that our integrated framework effectively captures comprehensive spatial-temporal knowledge and achieves significantly higher accuracy than other baseline prediction methods, making it a promising solution for a wide range proactive configuration tasks in mobile mmWave networks.

Generative AI has garnered substantial attention due to the limited defect samples in the industrial Internet of Things (IIoT). However, addressing the challenge of few-shot defect detection in industrial edge networks remains a key issue. In this paper, we propose ABEL, a novel AI-generated content (AIGC)-based edge learning framework for fast and efficient few-shot defect detection. This framework facilitates fast few-shot defect detection by harnessing the capabilities of realistic sample synthesis and edge-based AIGC task execution. Specifically, we propose an energy-based model (EBM)-guided Langevin Markov chain Monte Carlo (L-MCMC) image generation algorithm, synthesizing high-resolution industrial defect samples for efficient few-shot defect detection. Then, we formulate a large-scale mixed cooperative-competitive AIGC computation offloading problem and propose an attention and memory-based multi-agent reinforcement learning (AMMARL) algorithm to ensure fast edge execution of heterogeneous defect samples generative tasks. Particularly, the challenges of partial observability and high-dimensional state space are addressed by introducing multi-head attention mechanisms and long-term memory modules. Comprehensive synthesis experiments are conducted utilizing real-world industrial datasets NEU-CLS and DeepPCB. The experimental results demonstrate the effectiveness of our framework and algorithm's effectiveness in efficiently synthesizing realistic industrial defect images and optimizing edge-based AIGC task execution.

The flexibility and low cost of unmanned aerial vehicles (UAVs) offer great potential for them in areas such as disaster relief, energy line inspection, and traffic monitoring. Multiple UAVs form an airborne UAV network to share geo-tagged observation data for better collaborative missions. Blockchain can solve the security threats caused by the environment’s untrustworthiness and the UAV networks’ openness. However, the key to sharing data in blockchain-assisted UAV networks is identifying and understanding observational data and providing authentication query services in free boundary spatial. This paper proposes a blockchain-assisted UAV network data-sharing framework based on Non-Fungible Token (NFT). First, we design a marking and describing data method based on NFT to help geo-tagged data be effectively understood. Moreover, we propose a free-boundary spatial index tree to manage data and provide efficient queries. Furthermore, combined with the consensus mechanism and the blockchain transaction tree, the proposed sharing framework can provide query results authentication. Compared with the existing schemes, analysis and experiments demonstrate that our scheme could support the arbitrary expansion of UAV flight range and the random distribution of observation data in space, save at least 22% of storage overhead and reduce more than 36% of query time overhead.

Data dissemination is critical for 6G autonomous driving (AD) service because of the extensive demand for real-time traffic information. However, the heavier data transmission burden and more stringent requirements of AD service bring challenges for current data dissemination methods. In this paper, we first propose a novel digital twin (DT)-based semantic dissemination architecture to better support 6G AD service. Under this architecture, an energy-efficient semantic communication mechanism is developed to reduce the data dissemination burden while keeping low semantic model update costs. Meanwhile, the DT network is leveraged to disseminate semantic data in parallel with the physical vehicular networks, which alleviates the physical transmission contention and improves the dissemination efficiency. Second, we design a deep-reinforcement-learning (DRL)-driven semantic data dissemination scheme for the proposed architecture, named Proximal-policy-optimization for Digital-twin-aided Data Dissemination (PD3), which seeks the optimal DT transfer and semantic transmission scheduling strategy. Finally, experimental results show that our approach surpasses the state-of-the-art methods by 18.36% lower dissemination delay and 4.51% higher dissemination ratio on average.

Federated semi-supervised learning (FSSL) has been perceived as a promising approach that leverages semi-supervised learning and federated learning (FL) to provide powerful privacy preservation while reducing the burden on human supervision. However, due to the lack of strict participant identification and the significant proportion of unlabeled samples, FSSL is more susceptible to covert backdoor attacks than traditional machine learning. To validate this speculation, a novel semantic-perturbed stealthy backdoor attack (SemSBA) scheme is proposed for FSSL-based systems. In SemSBA, we select original natural semantic features in the unlabeled training samples as backdoor triggers and then generate poisoned samples by adding adversarial perturbations that move them across the model decision boundary. With SemSBA, the adversary can trigger the hidden backdoor in the victim model during the inference stage without any deliberate modifications on testing samples. To further improve the strength and robustness of the attack, a pseudo label steering enhancement strategy is also designed to perturb the weakly-augmented version of unlabeled samples to induce target pseudo label allocations. Additionally, to improve the attack success rate, we amplify the weight of the local backdoored model during FSSL’s model aggregation process to manipulate the game between benign clients and malicious clients. Extensive experiments based on two benchmark datasets demonstrate that the proposed SemSBA scheme can achieve comparable stealthiness against existing attacks.

Differentially private distributed machine learning protects privacy by injecting artificial noise to the computing results. To further improve energy efficiency, the natural noise in the wireless environment can be used to protect privacy. In this paper, we study the problem of coded distributed machine learning over Gaussian multiple-access wireless channels to achieve differential privacy by exploiting the natural noise. Firstly, we propose an aggregation scheme using differentially private Lagrange encoding in a wireless environment, where the local computing results are uploaded to the master through orthogonal channels. Then, we develop an achievable privacy protection level to illustrate the impact of transmit power and power allocation on privacy. Additionally, we establish a theoretical convergence upper bound of the proposed scheme, providing a clear understanding of the potential limitations and capabilities of the system. Finally, we demonstrate a trade-off between system resource settings, convergence, and privacy protection levels through experiments. Specifically, increasing the signal-to-noise ratio (SNR) and power allocated for gradient computation leads to a decrease in the privacy protection level of the system and an increase in training accuracy. Moreover, reducing the dataset partitions results in better training accuracy.

The existing Artificial Intelligence (AI)-based industrial defect detection methods have received extensive attention in the industrial Internet of Things (IoT). However, due to the limited defect samples, it is difficult for discriminative models to achieve better performance in imbalanced learning. In addition, the privacy concerns surrounding sensitive information hinder the sharing of synthetic industrial data. In this paper, we propose a novel framework called the Differentially Private Generative AI-empowered Digital Twin (DPG-DT) framework, aiming to synthesize realistic samples while satisfying differential privacy and empowering the construction of digital space and its connection with physical space. Specifically, the core of the DPG-DT framework is the proposed Private Synthetic Industry Energy-guided model (PSIE), in which we privatize the energybased model-empowered Langevin Markov Chain Monte Carlo (MCMC) sampling method with Gaussian noise and random response. Our method could replace the conventional generator while guaranteeing privacy. Extensive experiments on real-world industrial datasets NEU-CLS and DeepPCB demonstrate that the proposed framework is capable of generating synthetic industrial images with both high fidelity and differential privacy. Moreover, the achieved downstream accuracy outperforms baselines by 23.9 % in industrial scenarios.

The emerging federated learning (FL) enables distributed data mining for Internet of Things (IoT) big data while avoiding data outsourcing privacy risks via local data training and knowledge (i.e., model) sharing. However, only simplified local knowledge sharing will also cause user privacy leaks due to advanced attacks (e.g., model inversion or gradient leakage). Further, how to realize fine-grained and personalized privacy protection for IoT users is still a challenge. In this paper, we first propose a hierarchical cloud-edge orchestrated federated learning architecture for IoT, named HCE-FL, which aims to provide intelligent and distributed data analysis for IoT users. To address the FL privacy issues, we then design a multi-level access control encryption-based IoT knowledge sharing approach for HCE-FL. In our approach, IoT users could be classified into different levels according to their individual privacy requirements. In addition, the proposed multi-level access control encryption algorithm could ensure the confidentiality of the IoT knowledge flow, which runs through local clients, edge sanitizers, and cloud servers in HCE-FL. Moreover, security theoretical analysis shows that our HCE-FL could satisfy“no read” and no write” security rules for the mandatory IoT knowledge access control. Finally, we conduct experiments based on classic MNIST and CIFARIO datasets to evaluate our HCE-FL. The experimental results demonstrate that our solution can achieve personalized privacy-preserving FL without losing IoT data availability and users can obtain better model accuracy and convergence rate through secure IoT knowledge access and sharing.

With the rapid development of the Internet of Things (IoT), millions of IoT devices are constantly generating massive amounts of data. The development of artificial intelligence (AI) and edge computing makes it possible to conduct data analysis and knowledge mining efficiently among IoT edge devices. Knowledge, including intermediate results and training models obtained by large amounts of redundant data, is the core and foundation of edge intelligence. However, the sharing and utilization of knowledge still face a series of security and privacy issues, such as illegal knowledge access, knowledge tampering, and privacy leakage. To address these issues, in this article, we propose a blockchain-based knowledge storage and sharing architecture that enables secure knowledge management in intelligent IoT. We first design a permissioned blockchain-based decentralized and trusted knowledge storage scheme, which includes the on-chain encrypted knowledge storage and an improved Delegated Proof of Stake (DPoS) consensus protocol. Besides, we propose a lightweight attribute-based searchable encrypted knowledge-sharing mechanism, in which fine-grained and privacy-preserving knowledge collaboration is achieved through smart contracts and keyword search. Moreover, we reduce the computing overhead of edge devices through the design of partial outsourcing decryption. Finally, we analyze the security performance of our system as well as verify its practicality and ability to reject dishonest servers by simulation.

Differential-private federated learning (DP-FL) has emerged to prevent privacy leakage when disclosing encoded sensitive information in model parameters. However, the existing DP-FL frameworks usually preserve privacy homogeneously across clients, while ignoring the different privacy attitudes and expectations. Meanwhile, DP-FL is hard to guarantee that uncontrollable clients (i.e., stragglers) have truthfully added the expected DP noise. To tackle these challenges, we propose a heterogeneous differential-private federated learning framework, named HDP-FL, which captures the variation of privacy attitudes with truthful incentives. First, we investigate the impact of the HDP noise on the theoretical convergence of FL, showing a tradeoff between privacy loss and learning performance. Then, based on the privacy-utility tradeoff, we design a contract-based incentive mechanism, which encourages clients to truthfully reveal private attitudes and contribute to learning as desired. In particular, clients are classified into different privacy preference types and the optimal privacy-price contracts in the discrete-privacy-type model and continuous-privacy-type model are derived. Our extensive experiments with real datasets demonstrate that HDP-FL can maintain satisfactory learning performance while considering different privacy attitudes, which also validate the truthfulness, individual rationality, and effectiveness of our incentives.

Traffic forecasting is essential in improving and maintaining safety and orderliness in intelligent transportation systems (ITS). As a deep learning approach, graph neural networks (GNN) based spatial-temporal association mining methods are promising in traffic forecasting. However, current GNN-based methods usually require a high number of training data, and when the sample volume is small, the performance of the model drops dramatically. The existing transfer methods can solve this problem by leveraging knowledge from other data-rich areas, but the domain adaption method with access to source data still faces the non-neglectable problem of private information leakage in the source area. A solution that can solve cross-area transfer without access to source data is still missing. In this paper, to fill the gap, we propose a Transferable Federated Inductive Spatial-Temporal Graph Neural Network (T-ISTGNN) framework to transfer spatial-temporal dependency information in cross-area data to accomplish traffic state forecasting. First, we introduce a multi-source model aggregation scheme based on federated learning to retain the traffic information of the source areas. Second, we propose a transfer method between source and target areas based on hypothesis transfer learning to achieve domain adaption under source domain data protection. Third, we propose a GNN-based method called Inductive Spatial-Temporal Graph Neural Network (ISTGNN) for traffic forecasting. Experiments on real-world datasets demonstrate that T-ISTGNN is capable of cross-area traffic state forecasting under the restriction of preserving the privacy of source areas.

The emergence of Digital Twin Edge Networks (DTENs) achieves the mapping of real physical entities to digital models of cyberspace. By offloading real-time mobile data to Mobile Edge Computing (MEC) servers for processing and modeling, communication-efficient Digital Twin (DT) services could be achieved. However, the spatio-temporal dynamic DT service demand stochastically generated by mobile users easily causes service congestion, which challenges the long-term DT service stability. Meanwhile, current DT services still lack long-term effective incentive designs for participants. To solve these issues, we design an incentive-based congestion control scheme for stochastic demand response in DTENs. First, we adopt the Lyapunov optimization theory to decompose the long-term congestion control decision into a sequence of online edge association decisions, with no need for future system information. We then present a contract-based incentive design to optimize the long-term profit of the DT service provider, comprehensively considering the delay sensitivity, incentive compatibility, and individual rationality. Finally, experimental simulations are carried out to verify the superiority of the proposed scheme with the base station dataset of Shanghai Telecom. Theoretical and simulation analysis demonstrates that compared with benchmarks, our scheme could effectively avoid long-term service congestion with an arbitrarily near-optimal profit.

Recently, wireless edge networks have realized intelligent operation and management with edge artificial intelligence (AI) techniques (i.e., federated edge learning). However, the trustworthiness and effective incentive mechanisms of federated edge learning (FEL) have not been fully studied. Thus, the current FEL framework will still suffer untrustworthy or low-quality learning parameters from malicious or inactive learners, which undermines the viability and stability of FEL. To address these challenges, the potential social attributes among edge devices and their users can be exploited, while not included in previous works. In this paper, we propose a novelSocialFederatedEdgeLearning framework (SFEL) over wireless networks, which recruits trustworthy social friends as learning partners. First, we build a social graph model to find like-minded friends, comprehensively considering the mutual trust and learning task similarity. Besides, we propose a social effect based incentive mechanism for better personal federated learning behaviors with both complete and incomplete information. Finally, we conduct extensive simulations with the Erdos-Renyi random network, the Facebook network, and the classic MNIST/CIFAR-10 datasets. Simulation results demonstrate our framework could realize trustworthy and efficient federated learning over wireless edge networks, and it is superior to the existing FEL incentive mechanisms that ignore social effects.

The integration of satellite communication technology and terrestrial infrastructure has resulted in an un-precedented increase in network services covering the world. The main effect of the rapid growth of satellite networks is a broader range of data exchange and business interaction between the internal and external systems, making the network boundaries blur or even disappear. As a result, traditional passive security mechanisms based on dividing network boundaries cannot provide sufficient protection. To address this issue, in this paper, we propose a zero-trust and edge intelligence (ZTEI) empowered continuous authentication for satellite networks. We build an improved zero-trust architecture (ZTA) for satellite networks, which expands the traditional zero-trust concept to the multi-dimensional zero-trust that focuses on subject, object, environment, behavior, and physical entity. Then we propose a continuous authentication scheme in the proposed zero-trust architecture, enabling proactive and continuous authentication by periodically monitoring and re-evaluating variable attributes throughout the request lifecycle. Besides, in this scheme, we also design a Neural-Backed Decision Trees (NBDTs) based edge intelligence algorithm to improve the authentication accuracy. Finally, we build a testbed to evaluate the performance of the proposed architecture. Compared with the attribute-based access control (ABAC) under the traditional zero-trust architecture, our proposed architecture can improve the authentication accuracy of dynamic illegal requests by about 27%. In addition, according to standard network performance evaluation criteria, the loss of processing performance caused by our solution is also within an acceptable range.

The traffic anomaly analysis in IoT-based intelligent transportation system (ITS) is crucial to improving public transportation safety and efficiency. The issue is also challenging due to the unbalanced distribution of anomaly data in IoT-based ITS, which may cause overfitting or underfitting in the training phase. However, some research on traffic anomaly analysis injected limited data to address the shortage of anomaly samples or even neglects this issue, which overlooks the potential representation of nodes in graph neural networks. In this paper, we propose an improved contrastive GNN-based learning framework for traffic anomaly analysis that alleviates the problem of imbalanced datasets in the training phase. In this framework, we provide a graph augmentation approach with coupled features to learn different views of graph data. Besides, we design an effective training method based on the contrastive loss for our framework, which can learn the better performance of latent representations utilized in the downstream tasks. Finally, we conduct extensive experiments to evaluate the performance of our proposed frame-works based on real-world datasets. We demonstrate that our framework achieves as high as 6.45% precision improvement compared to the state-of-the-art.

Quantum Key Distribution (QKD) is a recent technology for secure distribution of symmetric keys, which is currently being deployed to increase communications security against quantum attacks. However, the key rate achievable over a weak quantum signal is limited by the link performance (e.g., loss and noise) and propagation distance, especially in multi-node QKD networks, making it necessary to design a scheme to efficiently and timely distribute keys to the various nodes. In this work, we formulate, using a Mixed Integer Linear Programming (MILP) model, a novel Routing, Channel, and Key-rate Assignment (RCKA) problem for QKD with Quantum Key Pool (QKP), which exploits the opportunity of using trusted relays and optical bypass. Our formulation accounts for the possibility to build a quantum key distribution path that combines both quantum channels and trusted relays to increase the acceptance ratio of key rate requests. Leveraging different versions of the proposed MILP model, we evaluate several strategies exploiting different combinations of trusted relays and optical bypass for the RCKA problem. Results show how different trade-offs between security and resource-efficiency (expressed in terms of acceptance ratio of key rate requests vs. key storing rate in QKP) can be achieved when adopting trusted-relay and/or optical-bypass technologies. Trusted relays can provide a higher acceptance ratio when the number of QKD modules (transmitters or receivers) is sufficiently large, while optical bypass, which does not require the implementation of expensive trusted relays, is preferable when the number of QKD modules is a limiting factor.

The development of backhaul/fronthaul networks can enable low latency and high reliability, but nodes in future networks like Internet of Things (IoT) can conduct malicious activities like flooding attack and DDoS attack, which can decrease QoS of smart backhaul/fronthaul network. Timely detection of malicious nodes in future networks is significant for low-latency backhaul/fronthaul networks. However, conventional supervised learning-based detection models require abundant malicious training samples, while capturing adequate malicious samples can not meet the requirement of timely detection. In this paper, we propose a novel few-shot malicious node detection system for improving QoS of IoT backhaul/fronthaul network, which can detect malicious nodes with unknown malicious activities through a limited number of network traffic samples. In our proposed system, we first design a fresh IoT traffic sample processing approach, which integrates normal activity samples and known malicious activity samples to generate training pairs. Then, we design a metric learning-based malicious node detection model training method, which employs a contrastive loss over distance metric to distinguish between similar and dissimilar pairs of samples. Besides, the trained model can detect nodes with unknown malicious activities by comparing real-time samples with few-shot samples of malicious nodes. Finally, the proposed system is evaluated on a real-world IoT network dataset named N-BaIoT. The exhaustive experiment results show that our model can achieve an average accuracy around 97.67 % when detecting malicious nodes with unknown malicious activities, which is comparable to state-of-the-art supervised learning models while our model only needs 5-shot samples of malicious node.

In the 6G era, the Intelligent Internet of Vehicles (IIoV) usually faces multiple security threats, which causes a trade-off of computation resources between security defense and vehicular artificial intelligence (AI). On-demand resource allocation in accordance with attack strength is a must for 6G vehicular edge learning. The existing works just focus on realizing low latency for AI resource allocation in vehicular edge learning, which ignores vehicles’ high security-defense demands for computation resources in the face of attacks. To address this, this paper proposes an on-demand incentive mechanism to achieve coordinated optimization of security defense resource allocation over 6G vehicular edge learning. First, we propose budget-feasible incentive contracts for computation resource allocation based on vehicles’ security-defense demands, which maximizes the learning utility of each vehicle type with a particular demand level. The contracts are tailored with the optimal resource allocation and incentive rewards with respect to different demand sensitivities. Next, apart from minimizing the single iteration time with the designed contracts, we design an optimization model of learning parameters for local accuracy to minimize the overall iteration time. Finally, simulation results show the feasibility and efficiency of the security-defense recourse allocation. This work is significant to improve the defense capability of 6G vehicle-edge learning against dynamic threats.

Recently, edge artificial intelligence techniques (e.g., federated edge learning) are emerged to unleash the potential of big data from Internet of Things (IoT). By learning knowledge on local devices, data privacy preserving and Quality of Service (QoS) are guaranteed. Nevertheless, the dilemma between the limited on-device battery capacities and the high energy demands in learning is not resolved. When the on-device battery is exhausted, the edge learning process will have to be interrupted. In this article, we propose a novel wirelessly powered edge intelligence (WPEG) framework, which aims to achieve a stable, robust, and sustainable edge intelligence by energy harvesting (EH) methods. First, we build a permissioned edge blockchain to secure the peer-to-peer (P2P) energy and knowledge sharing in our framework. To maximize edge intelligence efficiency, we then investigate the wirelessly powered multiagent edge learning model and design the optimal edge learning strategy. Moreover, by constructing a two-stage Stackelberg game, the underlying energy-knowledge trading incentive mechanisms are also proposed with the optimal economic incentives and power transmission strategies. Finally, simulation results show that our incentive strategies could optimize the utilities of both parties compared with classic schemes, and our optimal learning design could realize the optimal learning efficiency.

Recently, the Internet of Medical Things (IoMT) could offload healthcare services to 5G edge computing for low latency. However, some existing works assumed altruistic patients will sacrifice quality of service for the global optimum. For priority-aware and deadline-sensitive healthcare, this sufficient and simplified assumption will undermine the engagement enthusiasm, i.e., unfairness. To address this issue, we propose a long-term proportional fairness-driven 5G edge healthcare, i.e., FairHealth. First, we establish a long-term Nash bargaining game to model the service offloading, considering the stochastic demand and dynamic environment. We then design a Lyapunov-based proportional-fairness resource scheduling algorithm, which decouples the long-term fairness problem into single-slot subproblems, realizing a tradeoff between service stability and fairness. Moreover, we propose a block-coordinate descent method to iteratively solve nonconvex fair subproblems. Simulation results show that our scheme can improve 74.44% of the fairness index (i.e., Nash product), compared with the classic global time-optimal scheme.

The cybertwin and 6G-enabled Industrial Internet of Things (6G-IIoT) are the critical technologies that create the digital counterparts for physical systems and enable the near-instant interconnectivity in the industrial domain. It is in demand but challenging to conduct the integrated design for 6G-IIoT, which intertwines the cyber subsystems, such as control, communication, computing (3C), and the physical industrial factories and plants. Therefore, the cybertwin, which synchronizes between the digital counterparts and its physical entities during the system runtime, is the ideal proving ground for conducting the integrated design on the highly intertwined 3C of 6G-IIoT. However, the cybertwin lacks artificial intelligence to capacitate the automated integrated design for the 6G-IIoT. In this article, we first demonstrate the architecture of the machine-learning-based cybertwin for 6G-IIoT. Then, we leverage deep reinforcement learning (DRL) to conduct the integrated design via systematic trial and error in the cybertwin model, which is otherwise costly and dangerous in real industrial systems. Moreover, we invent the adaptive observation window for deep$Q$-network (AOW-DQN), which generates system states adaptive to the control system’s physical dynamics. Finally, the experimental results demonstrate the effectiveness and efficiency of our approach. To the best of our knowledge, we are the first to present the machine-learning-based cybertwin for carrying out the integrated design on the 3C for 6G-IIoT.

Mobile Edge Computing (MEC) is a novel platform to bring computation resources close to local users in vicinity constrained, obtaining the nickname of Cloudlet on the edge of the network. However, due to users' behaviors, computation resources demands show spatial and temporal dynamics among different Cloudlets, which is hardly to achieve on-demand computation workload balance management. While vehicles, unique for their mobility and powerful on- board equipments, could act as computation resources transporters breaking geographically restriction, which have potential to balance computation demands in the city. To address the issue above, in this paper, we design a novel computation demand response management (DRM) mechanism called Vehicle-to-Cloudlet (V2C), considering the mobility of vehicles, computation states of vehicles, and computation demands of Cloudlets. There exists two phases in V2C mechanism: cognitive phase and game phase, respectively. In cognitive phase, which Cloudlets are computation-scarce and which vehicles are potential computation resources can be cognized. Then, in game phase, to simulate computation resources trading process among Cloudlet service provider and individual vehicles, we formulate a price-based two-stage Stackelberg game, jointly maximizing the utility of the Cloudlet and the individual utility of each vehicles. We prove that unique Nash Equilibrium (NE) and Stackelberg Equilibrium (SE) exist in this game and propose a gradient iterative algorithm to obtain the optimal solution. Finally, numerical simulations show that our solution has good scalability and also encourages vehicles to trade their own computation resources to the Cloudlet.

Currently, blockchain technology has been widely used due to its support of transaction trust and security in next generation society. Using Internet of Things (IoT) to mine makes blockchain more ubiquitous and decentralized, which has become a main development trend of blockchain. However, the limited resources of existing IoT cannot satisfy the high requirements of on-demand energy consumption in the mining process through a decentralized way. To address this, we propose a decentralized on-demand energy supply approach based on microgrids to provide decentralized on-demand energy for mining in IoT devices. First, energy supply architecture is proposed to satisfy different energy demands of miners in response to different consensus protocols. Then, we formulate the energy allocation as a Stackelberg game and adapt backward induction to achieve an optimal profit strategy for both microgrids and miners in IoT. The simulation results show the fairness and incentive of the proposed approach.

Nowadays, benefit from more powerful edge computing devices and edge artificial intelligence (edge-AI) could be introduced into Internet of Things (IoT) to find the knowledge derived from massive sensory data, such as cyber results or models of classification, and detection and prediction from physical environments. Heterogeneous edge-AI devices in IoT will generate isolated and distributed knowledge slices, thus knowledge collaboration and exchange are required to complete complex tasks in IoT intelligent applications with numerous selfish nodes. Therefore, knowledge trading is needed for paid sharing in edge-AI enabled IoT. Most existing works only focus on knowledge generation rather than trading in IoT. To address this issue, in this paper, we propose a peer-to-peer (P2P) knowledge market to make knowledge tradable in edge-AI enabled IoT. We first propose an implementation architecture of the knowledge market. Moreover, we develop a knowledge consortium blockchain for secure and efficient knowledge management and trading for the market, which includes a new cryptographic currency knowledge coin, smart contracts, and a new consensus mechanism proof of trading. Besides, a noncooperative game based knowledge pricing strategy with incentives for the market is also proposed. The security analysis and performance simulation show the security and efficiency of our knowledge market and incentive effects of knowledge pricing strategy. To the best of our knowledge, it is the first time to propose an efficient and incentive P2P knowledge market in edge-AI enabled IoT.