In recent years, significant advances in gait recognition have been seen, with many methods reporting high accuracy on certain datasets. However, domain shifts, such as distribution inconsistencies in viewpoint or clothing, can severely degrade the performance of these models on unseen target domains, hindering the widespread application of gait recognition. Some unsupervised domain adaptation (UDA) methods have been proposed to address this problem. However, these approaches require continual updates with target domain data, which is often difficult to obtain due to privacy concerns and deployment complexity. This paper presents GaitDG, a single-source domain generalization framework designed to enhance the generalization ability of gait recognition models for unseen target domains, requiring training on only one source domain without accessing target domain data. During training, GaitDG employs adversarial training to disentangle domain-specific and identity-specific features, enabling the discovery of latent sub-domains and the extraction of domain-invariant features. Furthermore, GaitDG supports the integration of data augmentation to diversify the source domain data. We also introduce a data augmentation method, Segmentation Model Transfer (SMT), to mitigate recognition performance degradation caused by variations in segmentation models. As a model-agnostic approach, GaitDG can directly enhance the cross-domain recognition performance of gait recognition models without altering their structure. Comprehensive experiments on widely used gait datasets demonstrate that GaitDG significantly improves the cross-domain recognition performance of several state-of-the-art gait recognition models.

The rapid proliferation of cellular vehicle-to-everything (C-V2X) communications calls for efficient radio resource management (RRM). Effective C-V2X systems require both ultra-low latency for V2V safety communications and high throughput for V2I services. Current systems struggle with coordinating heterogeneous requirements under rapidly changing channel conditions. To address this challenge, we propose a new framework that integrates Graph Neural Networks (GNNs) with decentralized federated learning(DFL). Our approach embeds a dynamic graph representation into the vehicular network, where communication links are modeled as graph nodes. To adapt to rapidly changing topologies, we adopt the enhanced Graph Sample and Aggregation (GraphSAGE) for scalable neighborhood aggregation. Additionally, we apply unsupervised primal-dual learning to parameterize RRM policies based on instantaneous channel conditions. To improve generalization across network, we introduce a federated model aggregation strategy that employs channel-state-aligned isomorphic GNNs. Experimental results demonstrate that, compared to traditional GNN-based benchmark solutions, our framework achieves near-optimal system throughput while maintaining low computational complexity.

Using Clustered Vehicular Federated Learning (CVFL) in vehicular networks can enhance model intelligence through distributed collaboration while preserving data privacy. CVFL groups clients with similar data distributions to reduce the impact of non-independent and identically distributed (non-iid) data on federated learning efficiency, thereby supporting realtime and dynamic traffic decision-making. However, in practical applications, the high mobility of vehicles and the intermittent connectivity of communication links make it challenging to flexibly determine the number of clusters and the vehicles within each cluster. To address these issues, we propose a Graph Neural Network(GNN)-based clustering scheme called GNN-CVFL. Our proposed scheme includes two modules: clustering and resource allocation. In the clustering module, we treat the clustering problem of vehicle clients as a node classification problem in GNN, using a GNN-based method to cluster clients accurately based on their data distribution. The proposed method can automatically determine the number of clusters and the vehicles within each cluster in real-time. Moreover, based on the clustering results, We use the Lagrangian relaxation method to dynamically allocate available bandwidth resources and CPU frequencies to minimize system latency, ensuring efficient and flexible service for all vehicles. Numerical results demonstrate the feasibility and efficiency of our proposed scheme.

With the advancement of intelligent driving technology, vehicular networks generate vast amounts of decentralized data that need to be processed. As a distributed paradigm, Federated Learning (FL) enables data integration and processing across various vehicles. However, traditional FL methods face significant challenges in vehicular networks, including high communication overhead and the difficulty of meeting strict latency and reliability requirements. To address these challenges, we propose a Multi-scale Semantic Selection-based FL (MSSFL) scheme, which integrates multi-scale semantic parameter selection and transmission optimization to reduce the system's communication cost. The proposed scheme selects parameters with high semantic importance and allocates bandwidth proportionally based on their quantity to enhance communication efficiency. We further formulate an optimization problem to minimize both parameters' transmission cost and upload delay. To solve this problem, we develop an alternating iterative solution using the block coordinate descent (BCD) method, which alternately optimizes the semantic parameter selection and bandwidth allocation strategy. Experimental results validate the effectiveness of the proposed framework in enhancing both communication efficiency and model accuracy.

Unmanned aerial vehicle (UAV) is a promising method for emergency communication due to its rapid deployment and flexible networking. However, the limitations of energy capacity and long communication distances between UAVs make it challenging to cover multiple different relief sites and provide continuous and uninterrupted network services. To this end, we propose a multi-UAV swarm planning strategy to solve the issue while minimizing energy consumption. We first propose a multidifferentiated periodic rotational path method to solve the energy capacity constraints of individual UAVs and ensure the stability of swarm services. Then, a dynamic tree strategy is utilized to support the continuous backhaul network of the UAV swarm, based on the distribution of disaster relief sites. Further, an ant colony-based path planning algorithm is designed to optimize the overall energy consumption of UAVs. Simulation results show that the proposed strategy can construct an efficient UAV swarm to support emergency communication and significantly reduce energy consumption compared to benchmarks.

To enhance service quality, wireless computing power networks (WCPNs) need to realize flexible scheduling and allocation of computation resources across heterogeneous computing servers. Due to large user scales and diverse computation tasks, it is difficult for the current WCPN to serve multiple users and handle multiple tasks concurrently. Graph learning is a promising approach that can learn the representations of nodes through graph structures, enabling the exploration of dependencies among multiple users and tasks, and thereby facilitating computation task offloading. In this paper, we propose a graph learning-based multi-user multi-task offloading scheme for WCPN. First, we propose a wireless computing power network with multi-user and multi-task in which users need to make full use of distributed computing resources through task offloading to ensure efficient task execution. We formulate a system energy consumption minimization problem to jointly optimize computation resources, transmission power, and task offloading. To address the problem, we utilize graph learning to transform the joint optimization problem into a graph regression problem and leverage line graph to explore the solution. Numerical results demonstrate that our proposed scheme can improve computation efficiency, enhance optimization performance, and maintain transferability compared with the benchmarks.

Blockchain technology presents significant security challenges despite its transformative impact on digital transactions and decentralized data management. Key vulnerabilities include insecure smart contract execution, data privacy risks on transparent ledgers, and susceptibility of certain consensus mechanisms to attacks. Trusted Execution Environments (TEEs) offer a robust hardware-based solution to these critical issues. By providing isolated execution spaces, TEEs safeguard code and data confidentiality and integrity, thereby fundamentally strengthening blockchain security. This paper presents a comprehensive analysis of TEEs in blockchain technology. First, we analyze the challenges inherent in blockchain systems and demonstrate the advantages of TEEs over current methods. A detailed analysis of TEE properties, variants, and evolution in the blockchain field is provided. Additionally, we explore innovative TEE-based solutions across three key application domains: consensus mechanism optimization, confidential computation and execution, and payment networks and financial applications. Furthermore, we propose a research agenda addressing current challenges such as vulnerabilities to side-channel attacks and dependencies on hardware trust assumptions. Finally, we propose five critical directions for future TEE-blockchain integration: enhancement of security and privacy protection with particular attention to the Trusted Computing Base (TCB) minimization, performance optimization through hardware architecture advancement, trust model refinement to reduce centralization, expansion of application scenarios through interdisciplinary collaboration, and development of cross-chain interoperability standards. Our work contributes to blockchain security knowledge and provides a roadmap for researchers and practitioners in this rapidly evolving field.

Vehicular digital twin networks (VDTN) is an emerging paradigm integrating physical vehicular networks with their virtual digital twins (DT) mirror, enabling real-time mapping, simulation, and optimization of complex systems. However, constrained resources, high data synchronization costs, and dynamic network conditions in vehicular networks may degrade the performance of DT. We consider the interaction between task performance guarantees and node resource constraints to adaptively determine collaborative task computation transfer optimization in VDTN. In this paper, we design a semantic-aware multi-task vehicular digital twin network model, where vehicles extract semantic representations to achieve lightweight data transmission and efficient DT synchronization. We formulate a problem of maximizing the average utility of DT tasks by jointly considering the synchronization performance of DT tasks and the resource consumption among heterogeneous nodes. To solve the formulated problem, we develop a dynamic collaborative task computation transfer algorithm involving the high mobility of vehicles and heterogeneous resources of nodes. The algorithm is optimized in two phases to maximize average utility. A coarse-grained policy space is first obtained through an adaptive multi-agent deep reinforcement learning approach, aiming to alleviate the policy space explosion caused by dynamic task requirements and heterogeneous node collaboration. Subsequently, a fine-grained policy is derived via a resource-aware refinement mechanism. Numerical results validate the effectiveness and robustness of our proposed algorithm.

The adoption of symmetric searchable encryption (SSE) has become increasingly common. However, many current SSE schemes assume an honest-but-curious cloud service provider (CSP) or necessitate significant overhead to manage a malicious CSP. Furthermore, most of these schemes are tailored for static datasets. Our paper presents an efficient SSE scheme that aims to address these challenges. To the best of our knowledge, this is the first scheme that supports dynamic datasets with forward and backward privacy, integrity verification of non-empty and empty search results, efficient search, non-interactive, light client, and both forward and inverted indexes simultaneously. In this paper, we present two novel approaches, Hexie and Jianding. Hexie implements secret sharing to conceal index entries, enabling dynamic updates, non-interactive interactions, and lightweight clients. To enhance the reliability of search results and address the problem of empty, incomplete, or inaccurate outcomes, we introduce the Jianding scheme as an extension of Hexie. It combines a chained MAC structure with a secret sharing scheme, which enables a client to verify the data integrity of the search result efficiently. Moreover, we propose graph-based dictionary sharding to enhance search efficiency. Finally, we conduct comprehensive experiments to validate the effectiveness of the proposed schemes.

With the increasing number of Internet of Things devices and sensors in vehicular network, a huge amount of data is generated. Vehicle Edge Computing (VEC) utilises the computation resources at the edge of the network and can efficiently process this big data through computational offloading techniques. However, due to the neglect of communication network relationships among vehicles, current Vehicle-to-Vehicle (V2V) computation offloading schemes encounter challenges such as high communication latency, substantial communication overhead, and the wastage of computation resources. To address these challenges, we design a computation offloading mechanism based on Federated Graph Neural Network (GNN) for vehicular networks, that is, vehicular FedGNN (V-FedGNN). Firstly, our modeling approach considers features including vehicle speed, location, available resources, and wireless network, which are embedded in the graph structure. Secondly, we design weighted vehicular communication network topology and propose weighted total delay optimization problem. Finally, this paper proposes a prediction model based on Federated Learning (FL) and GNN to minimize the weighted computation offloading delays among vehicle nodes. Experimental results demonstrate that our proposed scheme achieves high offloading prediction accuracy, with an average value of 98.1% and achieves low offloading latency, correspondingly.

Vehicle edge computing (VEC) leverages the computational and communication resources available from vehicles and mobile edge computing (MEC) servers to provide computing services for mobile vehicles. However, traditional task offloading and resource allocation methods based on deep reinforcement learning (DRL) often ignore the latent relationships between vehicles and MEC servers. This oversight results in a lack of robustness in highly mobile and complex environments. Therefore, this paper proposes a distributed dynamic task offloading and resource allocation (DDTORA) strategy in the context of vehicle-assisted multi-vehicle VEC scenarios. DDTORA aims to utilize idle computational resources of vehicles and find optimal task offloading and resource allocation schemes to minimize the weighted summation of latency and energy consumption for all tasks. To find the optimal solution, we propose a graph attention network based multi-agent deep reinforcement learning (GAMDRL) algorithm for distributed task offloading and resource allocation. Numerical simulations demonstrate that DDTORA converges faster than the benchmark algorithms, significantly reducing latency and energy consumption by 25.44% to 34.19%.

Federated learning (FL) is a distributed artificial intelligence (AI) paradigm that enables clients to exchange local updates and builds the global AI model on the central server. However, the performance of traditional FL is easily affected by poisoning attacks because the central server cannot check the validity of local updates. Moreover, traditional FL lacks an effective incentive mechanism to sufficiently motivate clients to update local models actively. To address the above problems, we first propose a blockchain-based FL (BFL) framework to defend against the poisoning attack in a decentralized manner while ensuring the high performance of the global model. Then we design an incentive mechanism based on the static game with incomplete information to encourage legitimate nodes to participate in model training and remove attackers from the BFL. Moreover, we find the Nash equilibrium where legitimate nodes can always defend against poisoning attacks and provide high-quality models. Security analysis and simulation results show the security and efficiency of the proposed schemes.

Unmanned aerial vehicles (UAVs) equipped with high definition (HD) cameras, intelligent sensors, computing, and communication modules can be deployed to execute crowdsensing tasks by leveraging federated learning (FL), e.g., air quality perception and ground target detection. FL can reduce transmission stress and protect data privacy when training models, which is suitable for resource constrained Internet of UAVs. Nevertheless, the incentive issues about information asymmetry and bounded rationality impede the applications of FL-enabled Internet of UAVs. The existing FL incentive approaches focus on the risk-free condition, where task publishers are capable of making decisions with complete rationality by utilizing expected utility theory. In fact, task publishers under risk conditions are often bounded rational, whose risk-awareness makes the utility models more sophisticated. To overcome the above problems, we present a prospect theory (PT)-based incentive mechanism for FL-enabled Internet of UAVs. We first leverage PT to model the task publisher’s risk-awareness behavior and construct the subjective utility model. Thereafter, we utilize the framing effect of PT to design the optimal contract to maximize the subjective utility. Simulation results demonstrate that, compared with the baseline method, the proposed incentive mechanism has better performance.

Federated learning (FL) is an efficient decentralized machine learning methodology for processing non-independent and identically distributed (non-IID) data due to geographical and temporal distribution differences. Non-IID data generally indicates substantial disparities in data distribution and features among clients. This assumption is completely different from the conventional assumption of independent and identically distributed (IID) data in which all clients’ data originates from the same distribution. There are many factors that affect the features of non-IID data, such as user preferences, data collection methods, and client characteristics. The factors of data distribution, category proportions, and feature representation also affect the statistical properties of non-IID data. This paper conducts an in-depth exploration of FL with the consideration of diverse features and statistical properties of non-IID data. Specifically, we first discuss the impact of non-IID data on communication efficiency, model convergence, and FL accuracy. The presence of non-IID data leads to increased communication overhead, imbalanced class distribution, and uneven local model updates. All of these affect FL convergence and performance. Then, we present the latest advanced techniques, such as data partitioning/sharing, client selection, differential privacy, and secure aggregation [1], which are used to address the challenges posed by non-IID data in terms of communication efficiency and privacy protection. Furthermore, we show the emerging applications and use cases of FL with non-IID data in various domains, such as healthcare, IoT, and edge computing. Overall, this survey provides a comprehensive understanding of FL with non-IID data, including the challenges, advancements, and practical applications in different areas.

Digital twin (DT) is a technology that precisely replicates physical entities and seamlessly connects physical entities with virtual counterparts, which facilitates precise understanding, optimization, and decision-making. DT network (DTN) can be regarded as an information-sharing network, comprising a constellation of interconnected DT nodes. This survey provides an in-depth exploration of the concepts and potential of DTN, with a particular focus on the role of machine and deep learning in improving the efficiency of DTN systems, including anomaly monitoring, system state estimation, resource allocation, task offloading, model optimization, and security and privacy protection. Incorporating machine and deep learning into DTN stands to revolutionize industries by enabling the extraction of critical insights, enhancing anomaly detection capabilities, refining the accuracy of predictive models, and optimizing the allocation of resources. Finally, we discuss the challenges and future research directions in the application of machine and deep learning in DTN.

Cross-domain collaboration under wireless communication scenarios has gained traction in Internet-of-Things (IoT) applications. Authentication is essential for ensuring the security of wireless IoT devices (IoTDs). However, the existing cryptographic and physical layer authentication schemes are unappealing in cross-domain scenarios due to the presence of resource-limited IoTDs, privacy concerns of cross-domain sharing, and the negative effect of malicious attackers. This paper proposes FedScatter, a lightweight cross-domain authentication scheme for securing wireless IoTDs using backscatter communication. First, device identity signatures are constructed by harnessing passive signal features generated from feather-light backscatter tags, incurring negligible overhead. Subsequently, a federated learning model is designed to aggregate device identity information across domains while respecting device heterogeneity and data privacy. A novel parameter aggregation algorithm is proposed to bolster authentication resilience and against malicious attacks to avoid model pollution by powerful attackers with substantial hardware resources. A FedScatter prototype is implemented and evaluated, demonstrating significant improvements over state-of-the-art works in both true positive rate and false positive rate under various attacks.

Cloud service models intrinsically cater to multiple tenants. In current multi-tenancy model, cloud service providers isolate data within a single tenant boundary with no or minimum cross-tenant interaction. With the booming of cloud applications, allowing a user to search across tenants is crucial to utilize stored data more effectively. However, conducting such a search operation is inherently risky, primarily due to privacy concerns. Moreover, existing schemes typically focus on a single tenant and are not well suited to extend support to a multi-tenancy cloud, where each tenant operates independently. In this article, to address the above issue, we provide a privacy-preserving, verifiable, accountable, and parallelizable solution for “privacy-preserving keyword search problem" among multiple independent data owners. We consider a scenario in which each tenant is a data owner and a user’s goal is to efficiently search for granted documents that contain the target keyword among all the data owners. We first propose a verifiable yet accountable keyword searchable encryption (VAKSE) scheme through symmetric bilinear mapping. For verifiability, a message authentication code (MAC) is computed for each associated piece of data. To maintain a consistent size of MAC, the computed MACs undergo an exclusive OR operation. For accountability, we propose a keyword-based accountable token mechanism where the client’s identity is seamlessly embedded without compromising privacy. Furthermore, we introduce the parallel VAKSE scheme, in which the inverted index is partitioned into small segments and all of them can be processed synchronously. We also conduct formal security analysis and comprehensive experiments to demonstrate the data privacy preservation and efficiency of the proposed schemes, respectively.

Federated learning is an emerging distributed learning paradigm which brings an efficient and privacy-preserving intelligent model for the Internet of Vehicles (IoV). Unfortunately, federated learning is vulnerable to abnormal model attacks as it is hard to authenticate model parameters. Abnormal local models may slow down the convergence rate, reduce the accuracy of global models, and even deliberately control the global model in the attackers' chosen way. Furthermore, an abnormal global model may deduce sensitive information about vehicles and hinder the execution of genuine tasks. Therefore, in this paper, we propose a parameter-authentication federated learning (PAFL) scheme that can protect privacy of vehicles, such as driving habits, and defend against abnormal model attacks simultane-ously. Concretely, we equip the federated learning framework with the zero knowledge proof and Pedersen commitment to prove and authenticate the reliability of model parameters. Security and privacy analysis, as well as performance evaluation show that the PAFL scheme can successfully detect abnormal models with higher detection rate and achieve more secure global aggregation than existing representative schemes.

With the development of artificial intelligence, more and more applications rely on a large amount of high-quality data. Due to data island and security concerns, most of data is scattered on various devices and difficult to obtain. Federated learning (FL) is a promising paradigm to allow distributed devices cooperating to train a shared model without sharing raw data. However, the traditional FL is easy to be attacked because of single-point failure and it cannot avoid devices uploading fake or low-quality model updates. To this end, blockchain is integrated into FL to establish a secure model training ecosystem by maintaining an immutably distributed ledger. However, different data quality of raw data, diverse energy resources of devices, and different trust degree of devices make it challenging for blockchain-enabled FL efficient and reliable. Therefore, in this paper, we design a fine-grained resource allocation scheme for blockchain-enabled FL with considering the credit of devices, data quality, and energy resources. We first propose a credit-based blockchain-enabled FL to jointly execute FL training and blockchain establishment. Then we formulate the resource allocation problem with considering credit, data quality, precision, latency, and energy resources. A deep-reinforcement learning based algorithm is designed to solve the problem, and BlockSim is used to build the blockchain-enabled FL platform. Simulation results demonstrate the effectiveness of our proposed scheme on precision, latency and energy consumption, compared with traditional blockchain-enabled FL.

Telemedicine systems have the potential to address the uneven distribution of healthcare resources and reduce the risk of doctor infection. Performance analysis of the telemedicine system under time-varying transmission delays is essential to use and optimize the system. However, existing performance analysis methods only consider the numerical deviation between signals but ignore the kinematic characteristics of the hardware devices, which causes signals unrealistic matching and inaccurate results. To this end, this paper proposes an accurate performance analysis algorithm by exploiting the kinematic characteristics of devices. Particularly, representative features such as displacement and inertia are first extracted from the devices motion. Then, the state criteria of the devices are formulated by the extracted features, which are also converted into additional constraints to improve the accuracy of signal matching in performance analysis. To verify the effectiveness of the proposed scheme, along with simulation, we also implement a prototype of the telemedicine system. The experimental results show that the proposed algorithm improves the hit rate to 95.68% and reduces the ambiguity rate by 73.5%, which is more accurate than the existing dynamic time warping algorithm.

Attacks against IoT have shown a rapid increase in both quantity and complexity. Analysts must handle massive alerts and determine the type of attack manually. In addition, the same attack activity may present polymorphism alert sequences due to overlapping attacks, adaptive attack strategy, error alerts, etc, which poses a severe challenge for human analysis. This manual-dependent and scenario-by-scenario security model is seriously overwhelming security analysts. This paper proposes a contextual-analysis-based clustering approach, CACluster, to aggregate similar attack activities end-to-end. It embeds alert context into vector space and uses an unsupervised clustering method to find similar attack activities based on domain matching and vector distance. Experimental results demonstrate that the CACluster could accurately aggregate similar attack activities, with 0.888 purity, reducing the number of attack activities by 84.8%. It will significantly cut down analysts’ workload.

With the evolution of attack tactics, cyber-attacks are presenting a sophisticated trend. The multi-step attack has become the mainstream attack form, where adversaries implement multiple attack steps to achieve their goals, which poses server challenges to attack detection. Traditional research mainly concentrates on how a particular attack step is exploited but fails to identify the whole attack activity automatically. Manual analysis is required to correlate multiple steps and determine the fine-grained type of attack activities, which is a heavy workload. In addition, the high error rate of alerts results in a negative impact on attack-activity detection performance.To address these challenges, we propose a framework, LActDet, to automatically identify attack activities from the raw alerts end-to-end. Firstly, it utilizes a document-embedding method to vectorize attack-event descriptions. Second, a seq2seq model is implemented to embed the attack-event sequence into the attack-phase sequence to represent the framework of attack activity, aiming at improving the fault tolerance for error alerts. In the end, we propose a temporal-sequence-based classifier to identify attack activities. Our experimental results demonstrate that LActDet achieves higher detection accuracy, lower artificial dependence, and less system overhead.

Digital Twin Edge Network (DITEN) is a new paradigm that constructs virtual models for resource allocation, system optimization, and fault prediction through real-time information sharing between physical entities and virtual environments. However, the existing DITEN faces challenges such as high computing requirements and complex network layouts. IRS is a novel type of artificial microstructured material that controls the angle and intensity of signals by manipulating reflecting units. Therefore, we address the limitations of computing capabilities and complex communication environments by incorporating IRS into the construction of DITEN. We get help from IRS to offload training tasks to edge servers at the physical network layer and create digital twin models to capture the real-time state changes of the physical network layer. Furthermore, we formulate a problem aimed at minimizing system latency and propose a federated deep reinforcement learning (DRL) algorithm to jointly optimize the system’s computing resources, offloading coefficients, and reflection link configurations. Experimental results demonstrate the convergence and performance improvements of our proposed algorithm under various scenarios and parameters.

Semantic communication provides a new paradigm that aims at serving upcoming intelligent transportation applications including autonomous driving and real-time video monitoring. However, the problem of computing efficiency and data privacy during semantic extraction and transmission remains unsolved that need to be further investigated. In this paper, an efficient federated learning-empowered vehicular semantic communication(FVSCom) framework is proposed by jointly considering computing efficiency and data privacy, where federated learning is used to perform semantic extraction. To measure the performance of FVSCom, a metric of semantic utility that jointly considers semantic timeliness and semantic fidelity is proposed. We further analyze the end-to-end delay of the FVSCom network and formulate the semantic utility maximization problem. A DRL-driven dynamic semantic-aware algorithm for semantic utility optimization in FVSCom is proposed. The proposed algorithm can guide the agent to approach the suitable policy of semantic extraction and resource allocation, and dynamically respond to the leave or exit of vehicles. Experimental results showcase the potential of the proposed method for achieving substantial advantages over comparison algorithms and demonstrate strong robustness concerning the departure or exit of vehicles.

Mobile edge computing (MEC) is envisioned as a promising solution to real-time services in Internet of Vehicles (IoV) by enabling edge caching, computing and communication. However, it is still challenging to implement multimedia streaming in MEC-based IoV due to dynamic vehicular environments and heterogeneous network resources. In this paper, we present an MEC-based architecture for adaptive-bitrate-based (ABR) multimedia streaming in IoV, where each multimedia file is segmented into multiple chunks encoded with different bitrate levels. Then, we formulate a joint resource optimization (JRO) problem by synthesizing heterogeneous edge cache and communication resource constraints, which aims at achieving both smooth play and high-quality service by optimizing chunk placement and transmission. For chunk placement, a multi-armed bandit (MAB) algorithm is proposed for online scheduling with low overhead but slow convergence. Further, a deep-Q-learning algorithm is proposed to improve cache reward and speed up convergence by using replay memory for repeatedly training. For chunk transmission, we design an adaptive-quality-based chunk selection (AQCS) algorithm, which determines bandwidth allocation and quality level based on a benefit function incorporating quality level, available playback time, and freezing delay. Lastly, we build the simulation model and give comprehensive performance evaluation, which demonstrates the superiority of proposed algorithms.

With the high flexibility of supporting resource-intensive and time-sensitive applications, unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) is proposed as an innovational paradigm to support the mobile users (MUs). As a promising technology, digital twin (DT) is capable of timely mapping the physical entities to virtual models, and reflecting the MEC network state in real-time. In this paper, we first propose an MEC network with multiple movable UAVs and one DT-empowered ground base station to enhance the MEC service for MUs. Considering the limited energy resource of both MUs and UAVs, we formulate an online problem of resource scheduling to minimize the weighted energy consumption of them. To tackle the difficulty of the combinational problem, we formulate it as a Markov decision process (MDP) with multiple types of agents. Since the proposed MDP has huge state space and action space, we propose a deep reinforcement learning approach based on multi-agent proximal policy optimization (MAPPO) with Beta distribution and attention mechanism to pursue the optimal computation offloading policy. Numerical results show that our proposed scheme is able to efficiently reduce the energy consumption and outperforms the benchmarks in performance, convergence speed and utilization of resources.

The cyber security situation is not optimistic in recent years due to the rapid growth of security threats. What's more worrying is that threats are tending to be more sophis-ticated, which poses challenges to attack activity analysis. It is quite important for analysts to understand attack activities from a holistic perspective, rather than just pay attention to alerts. Currently, the attack activity analysis generally relies on human resources, which is a heavy workload for manual analysis. Besides, it's difficult to achieve high detection accuracy due to the missing and false-positive alerts. In this paper, we propose a new framework, ActDetector, to detect attack activities automatically from the raw Network Intrusion Detection System (NIDS) alerts, which will greatly reduce the workload of security analysts. We extract attack phase descriptions from alerts and embed attack activity descriptions to obtain their numerical expression. Finally, we use a temporal-sequence-based model to detect potential attack activities. We evaluate ActDetector with three datasets. Experimental results demonstrate that ActDetector can detect attack activities from the raw NIDS alerts with an average of 94.8% Precision, 95.0% Recall, and 94.6% F1-score.

Studying networked systems in a variety of domains, including biology, social science, and Internet of Things, has recently received a surge of attention. For a networked system, there are usually multiple types of interactions between its components, and such interaction-type information is crucial since it always associated with important features. However, some interaction types that actually exist in the network may not be observed in the metadata collected in practice. This article proposes an approach aiming to detect previously undiscovered interaction types (PUITs) in networked systems. The first step in our proposed PUIT detection approach is to answer the following fundamental question: is it possible to effectively detect PUITs without utilizing metadata other than the existing incomplete interaction-type information and the connection information of the system? Here, we first propose a temporal network model which can be used to mimic any real network and then discover that some special networks which fit the model shall a common topological property. Supported by this discovery, we finally develop a PUIT detection method for networks which fit the proposed model. Both analytical and numerical results show this detection method is more effective than the baseline method, demonstrating that effectively detecting PUITs in networks is achievable. More studies on PUIT detection are of significance and in great need since this approach should be as essential as the previously undiscovered node-type detection which has gained great success in the field of biology.

The rapid development of industrial Internet of Things (IIoT) requires industrial production towards digitalization to improve network efficiency. Digital Twin is a promising technology to empower the digital transformation of IIoT by creating virtual models of physical objects. However, the provision of network efficiency in IIoT is very challenging due to resource-constrained devices, stochastic tasks, and resources heterogeneity. Distributed resources in IIoT networks can be efficiently exploited through computation offloading to reduce energy consumption while enhancing data processing efficiency. In this article, we first propose a new paradigm digital twin network to build network topology and the stochastic task arrival model in IIoT systems. Then, we formulate the stochastic computation offloading and resource allocation problem to minimize the long-term energy efficiency. As the formulated problem is a stochastic programming problem, we leverage Lyapunov optimization technique to transform the original problem into a deterministic per-time slot problem. Finally, we present asynchronous actor-critic algorithm to find the optimal stochastic computation offloading policy. Illustrative results demonstrate that our proposed scheme is able to significantly outperforms the benchmarks.

Driven by technologies such as mobile edge computing and 5G, recent years have witnessed the rapid development of urban informatics, where a large amount of data is generated. To cope with the growing data, artificial intelligence algorithms have been widely exploited. Federated learning is a promising paradigm for distributed edge computing, which enables edge nodes to train models locally without transmitting their data to a server. However, the security and privacy concerns of federated learning hinder its wide deployment in urban applications such as vehicular networks. In this article, we propose a differentially private asynchronous federated learning scheme for resource sharing in vehicular networks. To build a secure and robust federated learning scheme, we incorporate local differential privacy into federated learning for protecting the privacy of updated local models. We further propose a random distributed update scheme to get rid of the security threats led by a centralized curator. Moreover, we perform the convergence boosting in our proposed scheme by updates verification and weighted aggregation. We evaluate our scheme on three real-world datasets. Numerical results show the high accuracy and efficiency of our proposed scheme, whereas preserve the data privacy.

The rapid increase in the volume of data generated from connected devices in industrial Internet of Things paradigm, opens up new possibilities for enhancing the quality of service for the emerging applications through data sharing. However, security and privacy concerns (e.g., data leakage) are major obstacles for data providers to share their data in wireless networks. The leakage of private data can lead to serious issues beyond financial loss for the providers. In this article, we first design a blockchain empowered secure data sharing architecture for distributed multiple parties. Then, we formulate the data sharing problem into a machine-learning problem by incorporating privacy-preserved federated learning. The privacy of data is well-maintained by sharing the data model instead of revealing the actual data. Finally, we integrate federated learning in the consensus process of permissioned blockchain, so that the computing work for consensus can also be used for federated training. Numerical results derived from real-world datasets show that the proposed data sharing scheme achieves good accuracy, high efficiency, and enhanced security.

Network Function Virtualisation (NFV) aims to increase the deployment flexibility and integration of new network services with increased agility within operator's networks. Due to the promises of NFV, it is also considered as one of the building blocks for 5G and edge computing. However, the Intrinsic dynamic features of NFV and even rigorous requirements proposed by 5G and edge computing expose severe challenges to resource management in NFV. In this paper, We study the problem of Virtualised Network Function (VNF) chain placement in dynamic environment, and formulate it as Integer Linear Programming problem with taking the dynamic characteristics of resource allocation into consideration. Then we propose an efficient dynamic algorithm with provable competitive performance based on primal-dual approach combined with an efficient subroutine. The theoretic analysis shows our algorithm is (1 - 1/e)-competitive to offline optimal solution. Finally, We evaluate the proposed approach through extensive numerical simulations. Experiment results show that the proposed algorithm achieves near-optimal competitive ratio and has much better performances than several algorithms in many aspects.

The emergence of computation intensive and delay sensitive on-vehicle applications makes it quite a challenge for vehicles to be able to provide the required level of computation capacity, and thus the performance. Vehicular edge computing (VEC) is a new computing paradigm with a great potential to enhance vehicular performance by offloading applications from the resource-constrained vehicles to lightweight and ubiquitous VEC servers. Nevertheless, offloading schemes, where all vehicles offload their tasks to the same VEC server, can limit the performance gain due to overload. To address this problem, in this paper, we propose integrating load balancing with offloading, and study resource allocation for a multiuser multiserver VEC system. First, we formulate the joint load balancing and offloading problem as a mixed integer nonlinear programming problem to maximize system utility. Particularly, we take IEEE 802.11p protocol into consideration for modeling the system utility. Then, we decouple the problem as two subproblems and develop a low-complexity algorithm to jointly make VEC server selection, and optimize offloading ratio and computation resource. Numerical results illustrate that the proposed algorithm exhibits fast convergence and demonstrates the superior performance of our joint optimal VEC server selection and offloading algorithm compared to the benchmark solutions.

The emergence of computation intensive on-vehicle applications poses a significant challenge to provide the required computation capacity and maintain high performance. Vehicular Edge Computing (VEC) is a new computing paradigm with a high potential to improve vehicular services by offloading computation-intensive tasks to the VEC servers. Nevertheless, as the computation resource of each VEC server is limited, offloading may not be efficient if all vehicles select the same VEC server to offload their tasks. To address this problem, in this paper, we propose offloading with resource allocation. We incorporate the communication and computation to derive the task processing delay. We formulate the problem as a system utility maximization problem, and then develop a low-complexity algorithm to jointly optimize offloading decision and resource allocation. Numerical results demonstrate the superior performance of our Joint Optimization of Selection and Computation (JOSC) algorithm compared to state of the art solutions.

Unmanned Aerial Vehicles (UAVs) communications have received increasing attention in both military and civilian applications due to low cost and ease of deployment. Security is an unavoidable yet challenging issue during the data transmission process of communication networks. In this paper, we concentrate on the resource allocation in secure relay network assisted by a UAV in the presence of multiple eavesdroppers. Our target is to maximize the secrecy rate by jointly designing the transmit beamformer and artificial noise subject to the transmit power constraint of UAV. The resulting optimization problem is highly intractable and the key observation is that the original optimization problem can be equivalently transformed into a two- level problem. In particular, the inner-level problem can be solved by exploiting Semi-Definite Relaxation (SDR) and Charnes-Cooper transformation techniques, and the outer-level problem is handled by performing one-dimensional algorithm. Also, the tightness of the rank-relaxation is analyzed. Finally, simulation results are provided to validate the performance of our proposed scheme.