Federated learning is a machine learning paradigm through training on locally private data and aggregating local models to generate a federated model. However, due to the heterogeneity problems (data heterogeneity and model heterogeneity), federated learning suffers from convergence difficulties and excessive aggregation overhead on decentralized participants. Additionally, federated learning faces privacy concerns during the aggregation of local models. To this end, in this work, we propose FEDINF, an efficient and secure inference with federated participants. Specifically, FEDINF features the following characteristics. FEDINF overcomes convergence challenges through federated inference instead of federated training, which reduces computation and communication overhead. Moreover, we design secure computation protocols and aggregation mechanisms to measure contributions, and handle both data and model heterogeneity without sacrificing privacy. Results of experimental evaluations on common datasets demonstrate that the proposed FEDINF outperforms the existing federated learning approaches in terms of efficiency and heterogeneity.

To address the issue of spatiotemporal coupling in random charging loads caused by the large-scale integration of electric vehicles, which disrupts the dynamic stability of microgrids, a Lyapunov-based microgrid optimization scheduling method (LOSM) is proposed. The key innovation lies in its dual virtual queue system, which meticulously models the spatiotemporally coupled randomness of BSS operation without relying on any forecasting, setting it apart from traditional prediction-dependent approaches. First, an energy storage system model incorporating a dynamic energy management mechanism is established. In contrast to traditional forecasting-dependent methods, our approach introduces a virtual queue for the battery unit state of charge (SOC), which enables real-time adaptability and significantly reduces reliance on prediction accuracy. This mechanism accurately characterizes the time-varying charging and discharging processes, thereby mitigating the impact of power fluctuations caused by charging on system frequency stability. Subsequently, a spatiotemporally correlated virtual queue is constructed for the multimodal operation of the battery swapping station, further enhancing real-time tracking capability without requiring high-accuracy forecasts. This achieves multidimensional and precise tracking of its electrical energy state. By integrating these virtual queues with a penalty factor adjustment mechanism, the proposed method simultaneously optimizes operational economy and dynamic stability while satisfying system stability constraints. Simulation analysis under a typical diurnal residential load profile with a 50-EV battery swapping station and a significant penetration of wind and photovoltaic generation demonstrates that the proposed approach increases the revenue of the battery swapping station by 5.67% and reduces the start-stop frequency of the diesel generator by 37.04%. This study provides a theoretical foundation for the robust operation of microgrids in scenarios involving electric vehicle integration and serves as an important reference for establishing dynamic stability assurance mechanisms in new power systems.

For digital health platforms, the challenge is balancing patient privacy with the ability to match patients to the right providers quickly and accurately. Existing systems often suffer from privacy leakage, insufficient matching precision, and degraded performance when dealing with large-scale data. In this paper, we propose 4PM, a novel privacy-preserving patient-provider matching scheme that leverages secure computation to deliver strong privacy guarantees while ensuring efficient and accurate matching. Our method partitions patient data between two non-colluding servers via secret sharing, employing the optimized Millionaires' Protocol for secure ranking and leveraging oblivious retrieval techniques for privacy-preserving matching. 4PM significantly reduces the computational complexity of high-dimensional data, achieving end-to-end latency within 0.5 seconds in scenarios with 200 doctors and 200-dimensional symptom vectors. Our work contributes to fostering secure and trustworthy healthcare in the digital era.

With the help of advanced sensors, virtual reality (VR) apps provide users with an immersive experience, but they also have the potential to collect a wider range of user data compared to traditional web and mobile apps. As a result, increasing numbers of regulations are being introduced globally, emphasizing the need for app developers to provide privacy policies that inform users about data collection, usage, and sharing (CUS) process. Unfortunately, despite the significant efforts made by VR developers to improve app performance, it remains unclear how they ensure their privacy policies comply with regulations and meet user expectations. In this study, we proposeVPVetto automatically vet privacy policy issues for VR apps. We first summarize five vetting criteria based on a study of privacy policies from popular apps: availability, completeness, granularity, minimization, and consistency. We then dissect VR data and entity ontologies and manually generate VR-related CUS sentences to fine-tune privacy policy language models, overcoming performance degradation when handling VR domain-specific sentences. Finally, we construct the largest VR privacy policy dataset to date, namedVRPP, consisting of privacy policies from 11,923 VR apps across 10 mainstream platforms. These policies were crawled in late 2022 and early 2025 to investigate the evolution of the VR ecosystem. Our vetting process examines platform, app category, and longitudinal perspectives, revealing that VR privacy policies have shown severe privacy issues over the past few years, including limited availability, poor quality, coarse granularity, a lack of adaptation to VR-specific traits, and inconsistencies between CUS statements and actual app behaviors.

An attacker can determine if a specific input belongs to a deep learning model's training set by analyzing the complete confidence vector output, known as a membership inference attack. To counter this type of attack, a common defense strategy is to add adversarial noise to the confidence vector to enhance the model's resilience. However, existing research indicates that defenses against adversarial examples may introduce new security risks to membership inference defenses via adversarial examples. Against this backdrop, this paper proposes a more robust adversarial example defense strategy. By generating adversarial examples with distributions similar to normal samples, we can reduce the impact of distributional differences on the defense model's security. Leveraging normalizing flow, adding noise to the hidden layer of a flow model trained on normal samples generates adversarial examples that resemble normal ones, enhancing defense robustness. Additionally, limiting the information accessible to the attack model further strengthens robustness. To accelerate convergence, a bidirectional mean update method is employed. The proposed strategy demonstrates effectiveness not only in defending against membership inference attacks but also in mitigating attribute inference attacks. Finally, experiments on real-world datasets validate the effectiveness of the proposed strategy.

The rapid adoption of 5G technology and Internet of things (IoT) devices has fueled significant growth in intelligent applications, increasing their complexity beyond simple task definitions. Scheduling intelligent applications modeled as directed acyclic graphs (DAGs) has thus emerged as a crucial challenge. Our proposed solution is a deep reinforcement learning (DRL) framework that uniquely integrates proximal policy optimization (PPO) with a transformer-based module for scheduling DAG applications. Unlike other approaches that rely on predefined priorities or static optimization algorithms, our approach enables agents to autonomously explore task execution orders and dynamically adapt to changing network resource conditions, learning optimal scheduling strategies. The algorithm leverages transformers to handle complex task dependencies, minimizing application duration and user energy consumption by jointly optimizing application processing order, task priorities, transmit power, offloading decisions, and computational frequency. Through a series of simulations, we prove the effectiveness of the proposed algorithm and demonstrate the performance comparison under different settings, providing a more flexible and robust solution for DAG scheduling in edge networks.

As an emerging communication technology, fluid antenna (FA) offers remarkable diversity and multiplexing gains due to its port mobility, which significantly reduces transmission delays in communication processes. This capability makes FA a promising solution for enhancing mobile edge computing (MEC) by optimizing communication delay. This paper establishes an FA-aided MEC offloading architecture and proposes a game theory-assisted multi-agent deep reinforcement learning (DRL) scheme to minimize the system delay of MEC. We aim to address the joint optimization problem of FA port selection, beamforming, user transmit power design, and MEC server computation resource allocation. However, the dynamic nature of FA ports and the variability of the associated large number of parameters introduce significant challenges, such as non-convexity and high dimension, in the optimization problem. In this paper, we employ game theory to reduce the dimension of the optimization variables by modeling the power control problem among multiple users as a non-cooperative game. Therefore, we propose a multi-agent deep deterministic policy gradient (MADDPG) algorithm, featuring two types of agents that collaboratively solve the problem. Simulation results validate the effectiveness of the proposed scheme, achieving 19.1-65.8% lower delays than benchmarks in MEC efficiency across all scenarios.

This paper tackles the challenges of high energy consumption, limited computational resources, and communication delays in Federated Learning (FL) for multi-UAV communication systems. We propose an innovative FL-based object detection training framework designed for UAV applications. The framework first introduces a lightweight modification to the YOLOv12 model, significantly reducing its parameter count and computational complexity, which enables efficient model training without compromising detection performance. Furthermore, the framework employs a joint optimization strategy for local computation and communication, thereby effectively reducing energy consumption and overall training time. Experimental results on the VisDrone2021 dataset demonstrate that, while maintaining a detection accuracy of 76.7% mAP, the model reduces its parameter count by 78.9% compared to the original YOLOv12 and lowers the global training cost by 19.58%, achieving an optimal balance between accuracy, latency, and energy efficiency.

Traditional reinforcement learning methodologies, primarily based on multi-layer perceptron (MLP) architectures, require extensive, fully connected layers for complex nonlinear representations. Such an approach increases computational demands and enhances the likelihood of model overfitting. In this paper, we present an innovative reinforcement learning approach, leveraging the Kolmogorov-Arnold Networks (KAN) framework, to enhance decision-making processes and resource management strategies in edge networks. We develop a KAN-based hybrid proximal policy optimization algorithm (KANH-PPO) to address this issue. This algorithm effectively addresses the challenge of hybrid action spaces within edge networks, which include discrete action spaces characterized by computational offloading decisions and continuous action spaces characterized by power allocation. Furthermore, the KANH-PPO algorithm innovatively integrates the KAN architecture, significantly reducing the number of training parameters and enhancing the algorithm's fitting capability and overall performance. Simulation experiments indicate that our proposed KANH-PPO algorithm outperforms the benchmark algorithm in terms of convergence speed and edge network system power, and it requires significantly fewer training parameters than benchmark algorithms. This helps to reduce the power consumption of communication and promote the development of green communication.

Federated learning (FL) is a pivotal paradigm for decentralized model training while preserving data privacy. However, data heterogeneity among clients significantly degrades model performance and convergence efficiency. In response, we introduce a federated knowledge distillation mechanism, FedEXD, that addresses robustness and convergence in diverse client environments through a self-propelled learning architecture. FedEXD employs a novel density ratio-based data extraction algorithm, leveraging KLIEP to select representative data, enhancing global knowledge synthesis and local model adaptability while preserving privacy. Extensive evaluations on benchmark datasets demonstrate FedEXD's substantial improvements in efficiency and accuracy, demonstrating a substantial 1.51% accuracy improvement over state-of-the-art methods under firm heterogeneity while reducing communication rounds by over 46.3%. These findings underscore FedEXD's potential to advance FL systems' generalizability across complex, non-IID data distributions, offering a scalable solution for privacy-conscious, high-performance distributed learning.

Effective power line inspection is crucial for power grid maintenance and management. To address the issue of signal loss or signal weakness in remote suburbs and deep mountains, we presented a UAV patrolling system with hybrid communication modules and edge detection capabilities. This system first features the communication ability in different scenarios including the extreme signal loss case by incorporating the BeiDou Navigation Satellite System, short-message communication, the Internet of Things, and edge computing. Next, to accurately and timely detect the power line faults, such as exposed wire, thatch covering, and lead stem falling, under various conditions, an edge detection model employing YOLOv8 is proposed without the help of cloud centers and public communication networks. Finally, experiments are designed on our built UAV patrolling test bed with different use cases. Numerical results show that our proposed scheme could efficiently inspect the power line, especially in signal loss or weak areas, and have a high precision and low latency for line fault detection, compared to the YOLOv8 baseline algorithm.

With the rapid progress made in aerial computing technology and the increased popularity of fifth-generation (5G) networks, uncrewed aerial vehicles (UAVs) have been playing a crucial role in real-time data collection, processing, and transmission. However, due to the diversity in traffic generated by UAVs in various mission scenarios, there is a significant challenge posed in traffic classification. Therefore, a novel traffic classification model is proposed in this article on the basis of the spatial attention-enhanced convolutional neural network (SAE-CNN). This model proves effective in improving classification accuracy and latency, particularly in the context of various 5G services, such as enhanced mobile broadband (eMBB), ultrareliable low-latency communication (URLLC), and Internet service. Also, a 5G heterogeneous network platform is built to collect UAV-related aerial computing data, with extensive experiments performed to verify the superior performance of the SAE-CNN model compared to other state-of-the-art methods. The experimental results demonstrate that the proposed approach enables effective traffic management and classification for the application of UAV in complex 5G environments.

Secure data aggregation is a powerful strategy for ensuring both data availability and privacy protection in smart grids. However, existing methods face two significant challenges: first, the substantial increase in communication and computation costs caused by malfunctioning smart meters; second, the risk of identity privacy leakage. To address these issues, we propose an efficient, fault-tolerant, and dual privacy-preserving data aggregation scheme. Our scheme effectively eliminates reliance on a trusted authority (TA) by leveraging an enhanced Paillier cryptosystem and a dual-secret sharing mechanism while ensuring robust fault tolerance. Additionally, it incorporates a pseudonym mechanism to safeguard user identity privacy. To meet the statistical requirements of modern smart grids, the scheme extends support for multidimensional data aggregation. Security analysis confirms that the proposed scheme provides dual privacy protection, ensures semantic security, and resists collusion attacks among participants. Furthermore, performance evaluations demonstrate that the proposed scheme maintains low communication and computation costs. Specifically, in fault-tolerant aggregation scenarios, its computation costs remain significantly lower than that of existing schemes, highlighting its efficiency. These results affirm the scheme’s practicality for smart grid applications.

The implementation of the Internet of Things (IoT) technology has the potential to unleash the capabilities of generative artificial intelligence (GAI). However, integrating GAI with IoT introduces a significant challenge in managing the limited resources of edge networks. In this article, we propose a resource optimization framework for GAI in IoT systems to address this issue, leveraging a heterogeneous computing framework. We focus on the system utility maximization problem, which jointly optimizes transmit power, heterogeneous computing allocation, CPU-cycle frequency, GPU-cycle frequency, and task scheduling under the latency constraint. The optimal CPU-cycle frequency, GPU-cycle frequency, and computing allocation are obtained by employing data parallelism analysis. In particular, we develop a hierarchical soft actor-critic with an intrinsic curiosity (HSAC-IC) algorithm to determine the task scheduling strategy. The HSAC-IC algorithm utilizes a hierarchical strategy structure and an intrinsic curiosity module (ICM) to improve learning efficiency and performance, particularly in environments characterized by sparse rewards, high-dimensional action spaces, and complex tasks. Our simulations benchmark the HSAC-IC algorithm against two existing deep reinforcement learning (DRL) algorithms and three reference schemes. The results illustrate that our scheme significantly outperforms these alternatives, ensuring AIGC user service requirements, while minimizing service generation costs, and optimizing resource allocation by configuring the image quality strategy on edge servers.

A tensor-based anomaly detection framework for high-dimensional time series in edge–cloud environments is presented. It is capable of dealing with both point anomaly and pattern anomaly. The transformation of data to tensor is carried out by sliding window with full consideration of the time dimension. The high dimensionality of data is tackled with tensor dimensionality reduction. An efficient iterative tensor decomposition method with low rank approximation is developed to rapidly obtain an optimal core tensor. It retains key information of the original tensor and achieves dimensionality reduction at the same time. A key matrix factorization technique is employed to circumvent large amount of iterative calculation for singular vectors of matrices. For anomaly detection, a tensor-based statistical prediction model is devised to generate a predicted tensor. For the purpose of comparison, a reverse technique is used to transform the predicted tensor to the form of original data. The final anomaly detection is performed with least significant difference and majority voting. Extensive experiments are conducted with two notable real-world datasets in a specific edge-cloud environment. Our proposal is compared with six other popular methods in terms of performance metrics precision, recall, F1-score, AUC and delay. Experimental results show that our method is superior to the six other methods in both edge-cloud and pure cloud settings.

Decentralized identity (DID) is rapidly emerging as a promising alternative to centralized identity infrastructure, offering numerous real-world applications. However, existing DID systems are confronted with trust concerns, as any distributed node can act as a credential issuer and be considered trusted, which is impractical. Effective trust management (TM) protocols are critical for system trustworthiness but face two primary challenges: preserving user feedback privacy to meet regulation requirements and building resilience against trust attacks to prevent manipulation. While privacy-preserving TM protocols effectively safeguard sensitive data, they often obscure feedback, hindering anomaly detection and complicating efforts to counter trust attacks. To address these issues, we propose DidTrust, a novel decentralized identity trust management protocol that bridges data privacy and resilience to trust attacks. DidTrust features a feedback data privacy preservation protocol that conceals feedback data while maintaining authorizability and verifiability. It also implements countermeasures against cooperative and individual trust attacks, improving detection accuracy without compromising privacy. To improve efficiency, we introduce a feedback compression module for large-scale sparse matrices. Rigorous analysis proves DidTrust to be universally composable (UC) secure under a malicious model, and experiments demonstrate its improved computational and storage efficiency while achieving higher trust attack detection rates compared to BC-Trust.

Decentralized identity (DID) is a transformative paradigm that leverages blockchain, decentralized identifiers and verifiable credentials (VCs) to enable self-sovereign and decentralized identity management with myriad application areas. However, existing DID implementations are confronted with two key challenges: insufficient decentralization and vulnerability to mobile adversary attacks. First, they paradoxically introduce central identity resolvers, intermediaries or static committees to manage critical identity services, key management or credential issuance, which violates the decentralized controlling aim against a single point of failure. Second, these systems are vulnerable to mobile adversaries who can gradually compromise multiple nodes or committee members over a long period, eventually seizing control of the system. In this paper, we propose DP-DID, the first dynamic and proactive decentralized identity system specifically designed to resist mobile adversary attacks in dynamic committee settings. To eliminate centralized authorities, DP-DID leverages blockchain, dynamic committees and BLS1signatures, which achieves decentralization. In addition, we design a dynamic and batch proactive secret sharing (DBPSS) scheme for DP-DID to ensure proactive security against mobile adversary attacks. This is achieved by allowing at mostt(threshold) committees to be corrupted per period, with the set of corrupted committees changing dynamically even if all players are eventually compromised. By incorporating DBPSS, DP-DID achieves efficient key management for multiple users in dynamic settings, enhancing overall system scalability. Through rigorous analysis, DP-DID is proven to be forward secure and secure against mobile adversary attacks under a widely adopted malicious model. Extensive experiments show that DP-DID has efficient performance, and our DBPSS scheme outperforms FaB-DPSS by over 11.67× in key handover efficiency.

Benefiting from the outstanding advantages in speeding up task processing and saving energy consumption, vehicular edge computing has entered a period of rapid development. Given the sharp increase in application services, it is vital to fully utilize all available computation resources to guarantee personalized requirements from different users. Specially, a lot of idle vehicle resources can be exploited for task execution to improve the service experience. On the other hand, most works focus on the system performance and fail to guarantee diversified user demands. To this end, we propose a novel distributed collaborative computing scheme for task completion rate maximization (TCRM) in vehicular networks by taking into account both vertical and horizontal collaboration. The novelty of horizontal collaboration lies in the full use of available one-hop vehicle resources for task computing. In order to simultaneously guarantee the system-level performance and the user-level performance, TCRM aims to maximize the task completion rate while minimizing the energy consumption by intelligent resource optimization and task allocation. A TD3-based algorithm combined with the Dirichlet distribution is proposed to obtain the optimization decisions. Extensive simulations demonstrate that TCRM significantly improves performance compared to baseline algorithms.

In remote or disaster areas, where terrestrial networks are difficult to cover and Terrestrial Edge Computing (TEC) infrastructures are unavailable, solving the computation computational offloading for Internet of Vehicles (IoV) scenarios is challenging. Current terrestrial networks have high data rates, great connectivity, and low delay, but global coverage is limited. Space–Air–Ground Integrated Networks (SAGIN) can improve the coverage limitations of terrestrial networks and enhance disaster resistance. However, the rising complexity and heterogeneity of networks make it difficult to find a robust and intelligent computational offload strategy. Therefore, joint scheduling of space, air, and ground resources is needed to meet the growing demand for services. In light of this, we propose an integrated network framework for Space-Air Auxiliary Vehicle Computation (SA-AVC) and build a system model to support various IoV services in remote areas. Our model aims to maximize delay and fair utility and increase the utilization of satellites and Autonomous aerial vehicles (AAVs). To this end, we propose a Deep Reinforcement Learning algorithm to achieve real-time computational computational offloading decisions. We utilize the Rank-based Prioritization method in Prioritized Experience Replay (PER) to optimize our algorithm. We designed simulation experiments for validation and the results show that our proposed algorithm reduces the average system delay by 17.84%, 58.09%, and 58.32%, and the average variance of the task completion delay will be reduced by 29.41%, 48.74%, and 49.58% compared to the Deep Q Network (DQN), Q-learning and RandomChoose algorithms.

Facial expression recognition is a technology that involves analyzing and interpreting human facial expressions to determine individual expressions or states. Mobile crowdsensing (MCS), a promising sensing paradigm, makes it easy to capture facial images and benefits facial expression recognition. Existing inference models for facial expression recognition usually rely on facial feature vectors or facial images, increasing privacy concerns about expression. For this reason, this paper proposes a privacy-preserving facial expression recognition scheme through MCS, named RAPOO, which falls in a client-server architecture. Roughly speaking, a user captures facial images using mobile devices and requests a recognition service provided by a cloud computing center. To protect the privacy of expressions, our approach focuses on designing secure computation protocols required by facial expression recognition necessarily, such as secure vector distance calculation and secure top-$k$query. These protocols enable facial expression recognition over encrypted data directly. To speed up the recognition and store encrypted feature vectors, a$k$-D tree data structure is introduced. The security analysis confirms that RAPOO effectively preserves the confidentiality of personal expressions. Extensive experimental evaluations show that our solution obtains a three-order-of-magnitude speedup in terms of computational overhead compared with the state-of-the-art.

The rapid development of satellite technology has significantly enhanced satellite computing service capabilities, particularly in terms of its application potential for complex tasks such as hyperspectral image (HSI) processing. Satellite edge computing (SEC) substantially improves processing efficiency by transferring task processing to the satellite. At the same time, intelligent reflective surfaces (IRS) reduce the pressure on ground service center communication resources by optimizing communication links between satellites on the ground. However, existing works mainly optimize general computing tasks, resulting in limited performance when processing HSI tasks. This paper proposes an IRS-assisted HSI processing SEC system to achieve the optimal balance between HSI processing accuracy and system energy consumption. We formulate an optimization problem as a joint task covering HSI offloading, band selection, and IRS phase shift optimization to achieve optimal overall performance. To address the problem, we propose the joint feature iterative optimization (JFIO) framework for HSI processing, which generates optimized task offloading solutions through graph attention networks, utilizes multi-feature attention capsule networks to achieve efficient band selection, and combines this with IRS modules to optimize communication link conditions. Extensive experiments on various datasets demonstrate that the proposed framework achieves an excellent balance between accuracy and energy consumption, with its performance significantly outperforming other baseline methods.

Federated learning (FL) has received widespread attention from academia and industry because it overcomes traditional security limitations associated with model training data. However, the FL process is vulnerable to manipulation by locally malicious users, who can alter their local data, thus impacting the accuracy of the model’s training outcomes. Meanwhile, optimizing delay in FL needs to take individual client fairness into consideration. In this paper, we present a reputation-based model aggregation and resource optimization framework to enhance the efficiency and reliability of training in wireless FL systems. Particularly, we investigate a total delay minimization problem while ensuring fairness among clients, which jointly optimizes client scheduling, transmit rate, bandwidth proportion, and CPU frequency. Considering the non-convexity and high complexity of the objective function, we decoupled the optimal variables and designed an efficient algorithm. By doing this, the client scheduling policy is obtained by deep reinforcement learning. Then, the transmit rate allocation and bandwidth proportion are derived through the Lagrangian dual method. Finally, we attain the CPU frequency allocation via the adaptive harmony algorithm. Simulation results reveal that our algorithm can establish delay fairness among clients and balance convergence performance and delay.

Despite narrow beams with strong anti-interception capabilities, terahertz communications still face eavesdropping risks in short-range indoor networks. This paper investigates physical-layer security of downlink terahertz communications for indoor three-dimensional (3D) networks comprised of a large number of access points (APs), users, human blockages, and eavesdroppers. We propose two different artificial noise (AN)-assisted terahertz secure transmission schemes, namely the full-AN (F-AN) scheme and partial-AN (P-AN) scheme, under the nearest line-of-sight association (NLA) strategy. The F-AN scheme involves full APs emitting AN to deteriorate the reception of eavesdroppers, and the P-AN scheme selects only those APs with blocked links to the typical user to emit AN based on the unique blocking feature of terahertz. We first obtain the expression for association probability. Then, we determine the eavesdropping region covered by the 3D beam on the ground. We derive the connection outage probability and secrecy outage probability for the two schemes by calculating the Laplace transform of aggregate interference. Our results provide interesting insights into how the secrecy performance is influenced by various system parameters, including the densities of APs and blockages. Moreover, we show that the P-AN scheme outperforms the F-AN scheme regarding the average number of perfect links per unit area.

Virtual reality (VR) apps can harvest a wider range of user data than web/mobile apps running on personal computers or smartphones. Existing law and privacy regulations emphasize that VR developers should inform users of what data are collected/used/shared (CUS) through privacy policies. However, privacy policies in the VR ecosystem are still in their early stages, and many developers fail to write appropriate privacy policies that comply with regulations and meet user expectations. In this paper, we propose VPVet to automatically vet privacy policy compliance issues for VR apps. VPVet first analyzes the availability and completeness of a VR privacy policy and then refines its analysis based on three key criteria: granularity, minimization, and consistency of CUS statements. Our study establishes the first and currently largest VR privacy policy dataset named VRPP, consisting of privacy policies of 11,923 different VR apps from 10 mainstream platforms. Our vetting results reveal severe privacy issues within the VR ecosystem, including the limited availability and poor quality of privacy policies, along with their coarse granularity, lack of adaptation to VR traits and the inconsistency between CUS statements in privacy policies and their actual behaviors. We open-source VPVet system along with our findings at repository https://github.com/kalamoo/PPAudit, aiming to raise awareness within the VR community and pave the way for further research in this field.

Millimeter wave (mmWave) Device-to-Device (D2D) communication networks suffer high path loss and dynamic physical obstructions. Meanwhile, eavesdroppers can intercept confidential information by residing in the main or side lobe of the transmission beam. Fortunately, multiple distributed Reconfigurable Intelligent Surfaces (RISs) offer a valuable approach to support mobile D2D devices, mitigating blocking effects and enhancing data security. In this paper, we propose a deep reinforcement learning (DRL) based communication scheme for the multi-RIS aided dynamic mmWave D2D networks, which aims to maximize the total secrecy data volume of D2D users over each service period by jointly optimizing the RIS resource allocation and multi-RIS phase shift design. To implement the intelligent collaboration of the RISs, we design the DRL approach with a nested structure. Specifically, we adopt a proximal policy optimization (PPO) network with discrete actions to realize the RIS-User association. Subsequently, we integrate the multi-agent PPO (MAPPO) framework to derive the phase shift design, containing intricate dynamic competition and cooperation among RIS agents. In addition, we divide the RIS into multiple subarrays, each sharing the same reflection coefficient. This approach controls more RIS phases while ensuring training stability. Simulation results demonstrate that our scheme can effectively learn the communication strategy to enhance the secrecy performance of dynamic mmWave D2D networks.

Satellite Terrestrial Networks (STN) are known to enhance the quality of service and to provide a better user experience. However, STNs are primarily utilized as wide-range relays and are characterized by a lack of effective intersatellite collaboration. The communication efficiency and quality of near real-time remote sensing tasks in 6G space-air-ground integrated networks are enhanced by the proposed Orbital Edge Computing-Collaborative Offloading Scheme (OEC-COS), which utilizes Service Function Chains (SFC) and the processing and collaboration capabilities of satellite nodes to allocate near real-time remote sensing tasks to optimal satellite nodes for execution. The remote sensing task offloading problem has been formulated as a delay minimization problem, and the advantages of the OEC-COS scheme in terms of computational resource utilization ratio and latency are validated through simulation experiments by comparing it with average orbit allocation and co-orbit allocation schemes. The proposed OEC-COS scheme achieves the lowest average task computing delay among these methods.

The fronthaul network architecture is the key to dealing with the massive traffic effectively and providing high-quality service, and the multiple base stations (BSs) deployed by it face the gigantic data transmission, which has given the demand for high-capacity communication and information security in the vehicular network. In this paper, we combine the millimeter wave (mmWave) communication and non-orthogonal multiple access (NOMA) technologies to escalate the communication capacity of multiple vehicle users (VUs), and propose a blockage-based cooperative jamming strategy to solve potential security risks in the vehicular network. In particular, with the help of jam-mers selected by this strategy, transmission security is enhanced simultaneously without escalating the instability of connections caused by the time-varying nature of vehicular networks under the NOMA transmission mechanism when the base station (BS) does not fully understand the channel state information (CSI) of VUs. Then we comprehensively analyze the specific distribution of roadways and the distance distribution of VUs under the NOMA strategy, and derive the performance metrics of the network based on the stochastic geometry method. Numerical results show that the proposed cooperative jamming scheme can effectively improve the secrecy performance of the vehicular network.

Compared with cloud computing, edge computing can provide users with computing services that lower response latency and reduce bandwidth pressure, enabling jobs to be processed in the proximity of users. Due to diverse user requirements and limited network resources, it is crucial to guarantee user experience through efficient task scheduling. However, the complexity of network environments and the inherent dependencies between different tasks from each job make it challenging. Given the dynamicity of network conditions, computation resources and service requirements in wireless networks, we have provided a two-level elastic scheduling scheme for dependent task processing. First, a novel scheduling architecture is presented to decouple executor deployment and task assignment, facilitating the increase of resource utilization and the flexibility and elasticity of task scheduling. Then, an optimization problem has been formulated to minimize the execution delay of all jobs with consideration of the characteristics of network networks and task dependencies. After that, an enhanced first come first serve strategy has been employed to make task assignments based on the devised task sorting algorithm. Finally, extensive simulations have been done to evaluate the performance of our proposed algorithm, and the results have shown that our proposed algorithm performs better than benchmark algorithms.

Artificial Intelligence (AI) tasks represent a substantial portion of the current workload within edge networks. However, existing centralized task scheduling approaches in network environments fall short of meeting the performance requirements of a diverse range of tasks. In response to this challenge, this paper introduces a finely-grained distributed task scheduling framework tailored to manage AI tasks efficiently. Specifically, we address the joint optimization problem of minimizing task completion time and maximizing server resource utilization. This involves the coordinated adjustment of task scheduling decisions, CPU/GPU frequencies, bandwidth allocation, and task deployment, all while adhering to constraints such as latency and energy consumption. To tackle this non-convex optimization problem, we adopt a multi-resource-objective-based multi-agent reinforcement learning (MRO-MARL) algorithm. This algorithm demonstrates adaptability to complex and dynamic environments where multiple resources require management. Its inherent flexibility facilitates the efficient scheduling of AI tasks within edge networks. Simulation results confirm the superior convergence and task execution efficiency of the proposed algorithm compared to baseline algorithms.

The combination of millimeter-wave (mmWave) and massive MIMO techniques can fulfill high data rate requirements for vehicular networks. However, due to the elevated path loss and severe blocking effects in mmWave propagation, the downlink data service of vehicles will seriously deteriorate. Fortunately, reconfigurable intelligent surface (RIS) can serve as a single-user relay to mitigate individual performance degradation without additional power consumption. In this paper, we propose a deep reinforcement learning (DRL)-based joint user schedule and RIS-User pairing scheme for the dynamic mmWave vehicular network to alleviate the blocking effects and maximize the total transmission data volume while ensuring the quality of service (QoS) for all target vehicles. In this scheme, each target vehicle has a distinct QoS constraint called minimum service data volume, which is a long-term and posterior optimization problem. Thus, QoS constraints are introduced in the reward design of the DRL algorithm, and the problem of high-dimensional action spaces is addressed by utilizing two nested Dueling Double-DQN (D-D3QN) networks. Simulation results demonstrate the superiority of our scheme in mmWave vehicular networks.

Due to the challenges of traditional machine learning in terms of data privacy and transmission efficiency, an efficient and private distributed training framework, namely federated learning (FL), is emerged. In the FL training process, users only need to upload to the server, thus preserving user privacy data and improving transmission efficiency. The computing network can provide sufficient computing power support for federated learning training. However, FL still faces many difficulties, such as dynamic wireless channels, limited local computing resources, data heterogeneity, and malicious data attacks. To tackle these challenges, it is crucial to select reasonable clients to participate in training. In this paper, we propose a client selection strategy that considers data quality, computing capacity, and radio resources. We first define a data quality metric by measuring the heterogeneity and reliability of the local dataset. Based on this, we formulate a joint optimization problem of client selection and resource allocation to minimize the average time delay and power consumption while maximizing data quality. Considering the dynamic of wireless channels and computing frequency, an online learning algorithm based on multi-armed bandit (MAB) is developed to obtain the client selection. Finally, a large number of simulations are carried out to verify the effectiveness of the proposed algorithm. The evaluation in different scenarios shows that the DQ-UCB algorithm can discard the attacked clients and the clients with poor computing power or channel quality to achieve better performance.

Ensuring reliable communication can be incredibly challenging in emergencies due to the breakdown of conventional infrastructure. However, a promising solution is on the horizon: the integration of reconfigurable intelligent surfaces (RIS) onto unmanned aerial vehicles (UAV), known as UAV-RIS. This innovative approach holds the potential to offer agile and adaptable communication services during crises, overcoming the limitations of traditional systems. This paper establishes an innovative UAV-RIS system with an active RIS to enhance the uplink communication between ground devices (GDs) and the air base station (ABS). We present an advanced communication strategy utilizing deep reinforcement learning (DRL) for UAV-RIS-supported uplink communication in dynamic emergencies. This scheme is designed to optimize the energy efficiency of the UAV-RIS communication system while adhering to quality of service (QoS) constraints for all GDs. It achieves this by jointly optimizing the trajectory of the UAV-RIS and the phase of the active RIS, ensuring efficient and reliable communication in challenging environments. To optimize the performance of the system, we propose a hierarchical Proximal Policy Optimization (H-PPO) algorithm and the upper and lower layers of H-PPO optimize the trajectory and phase control, respectively. Simulation results demonstrate that our scheme can effectively learn the communication strategy to enhance the performance of dynamic emergency communication networks.

The massive data transmission in vehicular networks has given rise to the demand for high-capacity communication and information security. In this paper, we combine the millimeter wave (mmWave) communication and non-orthogonal multiple access (NOMA) technology to escalate the communication capacity of multiple vehicle users (VUs), and design artificial noise (AN)-based secure transmission schemes for this new NOMA-mmWave communication architecture. The AN beamforming matrix is derived from the mmWave discrete angular channel model to fully exploit the characteristics of mmWave propagation and facilitate the analysis. Then we comprehensively analyze the specific distribution of roadways and the distance distribution of VUs under the NOMA strategy, and derive the analytical expressions for the performance metrics. Numerical results demonstrate that the proposed scheme can effectively improve the secrecy performance of the NOMA-mm Wave vehicular communications.

Abstract The threat of Scan and Foothold Attack to the Network Edge (SFANE) is increasing, which greatly affects the application and development of edge computing network architecture. However, existing works focus on the implementation of specific technologies that resist the SFANE but ignore the effectiveness analysis of them. To overcome this limitation, this paper constructs probabilistic models for evaluating network edge's resistance against SFANE. In particular, the attacker models of the SFANE based on the ATT&CK model are first formalized. Afterward, according to the state‐of‐the‐art defense technologies, three different defense strategies are illustrated: no defense, address mutation, and fingerprint decoy. Subsequently, three different probabilistic models are constructed to provide a deeper analysis of the theoretical effect of these strategies on resisting the SFANE. Finally, the experimental results show that the actual defense effect of each strategy almost perfectly follows its probabilistic model.

The traditional data security systems have the problems, such as poor adaptability, technical barriers, and closed interfaces, which cannot meet the development requirements of beyond 5G (B5G) and the Internet of Things (IoT). In this article, we design a novel deployment network framework for adaptive security by using blockchain technology in the software defined network (SDN)-enabled mobile edge computing (MEC) system. The blockchain is deployed on multiple SDN servers, ensuring decision consistency and data security. The distributed SDN controllers can schedule and combine atomic security functions (ASFs) from the security resource pool of the MEC system to provide comprehensive security services. Furthermore, we developed a multiagent deep deterministic policy gradient (MADDPG) scheduling optimization algorithm to enhance the utility of our model while optimizing latency and energy cost. Simulations indicate that the algorithm successfully maximizes the overall utility of the MEC system, while adhering to the constraints of latency and energy cost.

Metaverse is a visually rich virtual space in which users can interact with each other. By introducing metaverse into vehicular networks, vehicular metaverse can provide users real-time immersive experiences based on augmented technologies. Vehicular edge computing is a desirable approach to support computation-intensive vehicular metaverse services by network resource collaboration. User collaboration needs to reach a consensus on perception information, operation control and so on to realize user autonomy. However, the existing consensus algorithms often require computational proof or frequent communication, making them unsuitable for dynamically changing vehicular edge metaverse with low latency and energy restrictions. In this paper, we have proposed a reputation model maintained in the vehicular edge metaverse to score the vehicles, so the vehicles with a high reputation can be selected to participate in practical Byzantine fault tolerant (PBFT) consensus, which improves the probability of success and credibility of consensus without increasing the number of participating vehicles. Meanwhile, an optimization problem is formulated for each vehicle to allocate its computation and communication resources to reach a PBFT consensus. Also, the optimized communication time interval of each phase in the PBFT consensus can be used as a reference for setting the agreed upper time, which reduces the waiting time of vehicles and the probability of re-consensus. Simulation results have demonstrated that the proposed scheme effectively achieves PBFT information consensus with lower latency and energy consumption, and thus is more scalable and efficient.

Federated learning (FL) is a viable technique to train a shared machine learning model without sharing data. Hierarchical FL (HFL) system has yet to be studied regrading its multiple levels of energy, computation, communication, and client scheduling, especially when it comes to clients relying on energy harvesting to power their operations. This paper presents a new two-phase deep deterministic policy gradient (DDPG) framework, referred to as “TP-DDPG”, to balance online the learning delay and model accuracy of an FL process in an energy harvesting-powered HFL system. The key idea is that we divide optimization decisions into two groups, and employ DDPG to learn one group in the first phase, while interpreting the other group as part of the environment to provide rewards for training the DDPG in the second phase. Specifically, the DDPG learns the selection of participating clients, and their CPU configurations and the transmission powers. A new straggler-aware client association and bandwidth allocation (SCABA) algorithm efficiently optimizes the other decisions and evaluates the reward for the DDPG. Experiments demonstrate that with substantially reduced number of learnable parameters, the TP-DDPG can quickly converge to effective polices that can shorten the training time of HFL by 39.4% compared to its benchmarks, when the required test accuracy of HFL is 0.9.

Evolutionary algorithms (EAs), such as the genetic algorithm (GA), offer an elegant way to handle combinatorial optimization problems (COPs). However, limited by expertise and resources, most users lack the capability to implement EAs for solving COPs. An intuitive and promising solution is to outsource evolutionary operations to a cloud server, however, it poses privacy concerns. To this end, this article proposes a novel computing paradigm called evolutionary computation as a service (ECaaS), where a cloud server renders evolutionary computation services for users while ensuring their privacy. Following the concept of ECaaS, this article presents privacy-preserving genetic algorithm (PEGA), a privacy-preserving GA designed specifically for COPs. PEGA enables users, regardless of their domain expertise or resource availability, to outsource COPs to the cloud server that holds a competitive GA and approximates the optimal solution while safeguarding privacy. Notably, PEGA features the following characteristics. First, PEGA empowers users without domain expertise or sufficient resources to solve COPs effectively. Second, PEGA protects the privacy of users by preventing the leakage of optimization problem details. Third, PEGA performs comparably to the conventional GA when approximating the optimal solution. To realize its functionality, we implement PEGA falling in a twin-server architecture and evaluate it on two widely known COPs: 1) the traveling Salesman problem (TSP) and 2) the 0/1 knapsack problem (KP). Particularly, we utilize encryption cryptography to protect users' privacy and carefully design a suite of secure computing protocols to support evolutionary operators of GA on encrypted chromosomes. Privacy analysis demonstrates that PEGA successfully preserves the confidentiality of COP contents. Experimental evaluation results on several TSP datasets and KP datasets reveal that PEGA performs equivalently to the conventional GA in approximating the optimal solution.

Smart meter-based individual load forecasts are more and more widely deployed to serve smart grid and home energy management. Customary load forecasting systems collect a massive amount of fine-grained electrical data from people’s smart meters in plaintext, inevitably raising privacy concerns and even anti-smart-meter initiatives. Current privacy solutions either compromise accuracy and efficacy or require the redeployment of trusted infrastructure. In this paper, we present PrivGrid, the first systematic solution for smart grids that collects, clusters, trains, and forecasts customers’ load data in a privacy-preserving way. Moreover, we highlight the technical contribution of our building block: a novel and fast arithmetic multiplication triple via secure inner product protocol outperforms the existing methods and may be included in other privacy computing modules. Then, we develop efficient secure protocols to enable the arithmetic operations of individual load forecasting in a server-aided model and utilize the best alternatives to nonlinear functions. Besides, aggregating all of our individual forecasts can produce a more accurate estimate of the system-level load than the typical aggregate technique. We rigorously prove that the servers cannot obtain the user’s historical load data and short-term load forecast values while providing services. PrivGrid is also tested on real residential smart meter data to show its efficiency, and the relevant code has been made available to the community for further research.

Secure outsourced computation is critical for cloud computing to safeguard data confidentiality and ensure data usability. Recently, secure outsourced computation schemes following a twin-server architecture based on partially homomorphic cryptosystems have received increasing attention. The Secure Outsourced Computation on Integers (SOCI) toolkit is the state-of-the-art among these schemes which can perform secure computation on integers without requiring the costly bootstrapping operation as in fully homomorphic encryption; however, SOCI suffers from relatively large computation and communication overhead. In this paper, we propose SOCI+ which significantly improves the performance of SOCI. Specifically, SOCI+ employs a novel (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption as its cryptographic primitive, and supports a suite of efficient secure arithmetic computation on integers protocols, including a secure multiplication protocol (SMUL), a secure comparison protocol (SCMP), a secure sign bit-acquisition protocol (SSBA), and a secure division protocol (SDIV), all based on the (2, 2)-threshold Paillier cryptosystem with fast encryption and decryption. In addition, SOCI+ incorporates an offline and online computation mechanism to further optimize its performance. We perform rigorous theoretical analysis to prove the correctness and security of SOCI+. Compared with SOCI, our experimental evaluation shows that SOCI+ is up to 5.3 times more efficient in online runtime and 40% less in communication overheads.

Facial recognition technology has been developed and widely used for decades. However, it has also made privacy concerns and researchers’ expectations for facial recognition privacy-preserving technologies. To provide privacy, detailed or semantic contents in face images should be obfuscated. However, face recognition algorithms have to be tailor-designed according to current obfuscation methods, as a result the face recognition service provider has to update its commercial off-the-shelf (COTS) products for each obfuscation method. Meanwhile, current obfuscation methods have no clearly quantified explanation. This paper presents a universal face obfuscation method for a family of face recognition algorithms using global or local structure of eigenvector space. By specific mathematical explanations, we show that the upper bound of the distance between the original and obfuscated face images is smaller than the given recognition threshold. Experiments show that the recognition degradation is 0% for global structure based and 0.3%-5.3% for local structure based, respectively. Meanwhile, we show that even if an attacker knows the whole obfuscation method, he/she has to enumerate all the possible roots of a polynomial with an obfuscation coefficient, which is computationally infeasible to reconstruct original faces. So our method shows a good performance in both privacy and recognition accuracy without modifying recognition algorithms.

Mobile edge computing (MEC) offers promising solutions for various delay-sensitive vehicular applications by providing high-speed computing services for a large number of user vehicles simultaneously. In this paper, we investigate non-orthogonal multiple access (NOMA) assisted secure offloading for vehicular edge computing (VEC) networks in the presence of multiple malicious eavesdropper vehicles. To secure the wireless offloading from the user vehicles to the MEC server at the base station, the physical layer security (PLS) technology is leveraged, where a group of jammer vehicles is scheduled to form a NOMA cluster with each user vehicle for providing jamming signals to the eavesdropper vehicles while not interfering with the legitimate offloading of the user vehicle. We formulate a joint optimization of the transmit power, the computation resource allocation and the selection of jammer vehicles in each NOMA cluster, with the objective of minimizing the system energy consumption while subjecting to the computation delay constraint. Due to the dynamic characteristics of the wireless fading channel and the high mobility of the vehicles, the joint optimization is formulated as a Markov decision process (MDP). Therefore, we propose an asynchronous advantage actor-critic (A3C) learning algorithm-based energy-efficiency secure offloading (EESO) scheme to solve the MDP problem. Simulation results demonstrate that the agent adopting the A3C-based EESO scheme can rapidly adapt to the highly dynamic VEC networks and improve the system energy efficiency on the premise of ensuring offloading information security and low computation delay.

Millimeter wave (mmWave) with abundant spectrum resources can realize high-rate communications in vehicular networks. However, the mobility of vehicles and the blocking effect of mmWave propagation bring new challenges to communication security. Cooperative communication is envisioned as a promising physical layer security (PLS) approach to enhance the secrecy performance, but it will induce extra energy consumption of vehicles. This paper proposes a deep recurrent reinforcement learning (DRRL)-based energy-efficient cooperative secure transmission scheme in mmWave vehicular networks, where eavesdropping vehicles attempt to intercept the multi-user downlink communications. We jointly design the mmWave beam allocation, the cooperative nodes selection, and the transmit power of vehicles. Specifically, the mmWave base station selects idle vehicles as relays to overcome the severe blocking attenuation of legitimate transmissions and controls the transmit power to reduce energy consumption. Moreover, to ensure secure transmission, a cooperative vehicle is selected to transmit jamming signals to the eavesdropping vehicles while the legitimate users are not disturbed. We conduct comprehensive interference analysis for both direct transmission and relay-aided transmission, and derive the theoretical expressions for the secrecy capacity. We then design the Dueling Double Deep Recurrent Q-Network (D3RQN) learning algorithm to maximize the total secrecy capacity subject to the energy consumption constraint. We set the energy consumption punishment mechanism to avoid relay vehicles consuming too much power for forwarding signals. We demonstrate that the proposed scheme can rapidly adapt to the highly dynamic vehicular networks and effectively improve secrecy performance while reducing the energy consumption of vehicles.

Autonomous vehicle platooning has tremendous potential to relieve the burden of Vehicular Edge Computing (VEC) by sharing resources with nearby vehicles. Therefore, fleet formation and resource orchestration within vehicle platoons have recently ignited significant research interest. However, most fleet formation works focus on the intra-platoon configuration and information exchange, but few consider trajectory matching and joining willingness. Likewise, in multi-platoon scenarios, static resource orchestration for a single platoon no longer meets the demand from dynamic resource scheduling. To tackle these problems, we proposed the SFO scheme, an adaptive taskScheduling based on incentive fleetFormation and metrizable resourceOrchestration. First, we design a fleetFormation algorithm based onTrajectory matching andJoining willingness (FTJ) to ensure the stable underlying architecture. Second, we use theWeightedSum ofEnergyConsumption (WSEC) as the performance metric for resource orchestration and formulate the time-average WSEC minimization problem. Third, anAdaptive taskScheduling underPartitionableApplications and variableResources (ASPAR) is proposed for an asymptotic optimal solution in reaction to the changeable backlog of the timeout queue. Finally, our numerical results demonstrate that our approach is superior to other latest and classic works in energy consumption and execution latency.

Assigning sensing tasks to appropriate task participants is critical for mobile crowdsensing (MCS) and is an essential optimization problem. However, existing task assignment (or say participant selection) solutions for MCS generally support a single-objective optimization (e.g., minimizing travel distance or maximizing social welfare). Additionally, task assignment for MCS usually requires task participants’ and a task requester's location information, which compromises their location privacy and hinders participation willingness. To achieve task assignment with bi-objective optimization and safeguard bilateral privacy, in this paper, we propose RATE, a privacy-preserving task assignment with bi-objective optimization for MCS. RATE features the following characteristics. First, RATE enables task assignment with bi-objective optimization including maximizing the social welfare and the requester's revenue, simultaneously. Second, RATE achieves bilateral privacy-preserving task assignment with bi-objective optimization by carefully designing underlyingly secure computing protocols. Third, RATE approximates optimal results of task assignments without sacrificing privacy. Theoretical analyses show that RATE protects the location privacy of both the task requester and the task participants. Meanwhile, experimental evaluations demonstrate that RATE outperforms traditional task assignment solutions and generates the task assignment result effectively and efficiently.

Federated learning has been combined with graph learning for modeling spatial-temporal data while maintaining data confidentiality and safety. However, there are still several issues: 1) In practical usage, some clients may be unable to participate in the model inference due to poor network signal, malicious attacks, etc. 2) In the communication process, the uploaded information is easily disturbed by noise. The performance of the graph model will be seriously affected by its low robustness. Additionally, the assumption of identical distribution between the training and testing domain does not hold in practical scenarios, resulting in overfitting and poor generalization ability of the trained models. 3) The relations that exist among clients may change dynamically over time and manually constructing the graph structure of clients may not accurately represent the relations among clients. In this paper, we address all the above limitations by proposing a robust hierarchical split-federated graph model named DCSFG. Specifically, DCSFG combines split-federated learning and spatial-temporal graph model to better capture the spatial-temporal dependencies. We propose a Dropclient method and introduce the uncertainty estimation to enhance the robustness and generlization ability of the model. We also design a dual-sub-decoders structure for clients so that they can perform predictions locally and independently when they are unable to participate in the inference process. A novel hierarchical graph message passing structure is proposed to enable each client to perceive the global and local information. The extensive experimental results demonstrate the effectiveness of DCSFG.

Cyber-physical systems (CPS) offer integrated resolutions for various applications by combining computer and physical components and enabling individual machines to work together for much more excellent benefits. The ad hoc –based CPS provides a promising architecture due to its decentralized nature and destructive-resistance. A growing number of information leakage events in CPSs and the following serious consequences have aroused ubiquitous concern about information security. In this article, we combine physical layer security solutions and millimeter-wave (mmWave) techniques to safeguard the ad hoc network and investigate the reliability-security tradeoff by taking user demands for the network into account, where eavesdroppers attempt to intercept messages. For the secrecy enhancements, we adopt an artificial noise (AN) assisted transmission scheme, in which AN is employed to create non-cancellable interference to eavesdroppers. The reliability and security are correspondingly characterized by the connection outage probability and secrecy outage probability, and their analytical expressions of them are attained through theoretical analysis for the purpose of the tradeoff issue discussion. Our results reveal that secrecy performance in mmWave ad hoc networks gains significant improvement through the use of AN. It also shows that given total transmit power, there exists a tradeoff between reliability and security to achieve optimal outage performance.

Online syndicated lending offers quick and convenient financing support to individuals, while diversifying risks by pooling funds from multiple lenders into loan projects. It has experienced explosive growth, reaching a multibillion-dollar market. Establishing transparency is essential for constructing a trusted, fair, and regulation-compliant financial collaboration model. Meanwhile, confidentiality must be maintained to protect the sensitive financial information of individual lenders. Multi-party computation (MPC) can protect the input privacy of lenders, but it cannot safeguard the sensitive information revealed by the fund flow itself. To address these challenges, we propose a new collaborative financial ledger for online syndicated lending. It leverages homomorphic encryption/commitment to enable the reuse of intermediary states without compromising privacy throughout the entire lifecycle of a loan. This system also supports efficient regulation-compliant auditing. We streamline the framework design to optimize performance and develop a prototype system. Even with a large syndicate of 100 lenders, the system still achieves low-latency performance.

Sample alignment technique is a key component of vertical federated learning. One of the important solutions for sample alignment is known as private set intersection (PSI). It requires multiple participants to collaboratively compute the intersection from their samples while preserving data security and privacy. However, with a growing number of participants and samples, the communication and computation overhead of the multiparty PSI protocol becomes heavy, which severely impacts the performance of vertical federated learning. To improve the efficiency of sample alignment, this paper proposes a distributed multiparty PSI protocol based on fast Fourier transform (FFT) polynomial interpolation and oblivious pseudo-random function (OPRF). The scheme reduces communication complexity by FFT polynomial interpolation. Meanwhile, it employs OPRF to resist collusion attacks. We evaluate the performance of the scheme in two scenarios: without collusion and arbitrary collusion. The experimental results indicate that the scheme is a practical and efficient solution for sample alignment in vertical federated learning.

With the continuous development of mobile communication networks and artificial intelligence technology, the number of smart mobile devices has shown an exponential growth trend, and artificial intelligence (AI) jobs have developed unprecedentedly. However, it is difficult for resource-constrained mobile devices to meet the computational demands of these jobs. How to make full use of the dynamic resources in the wireless network to achieve efficient execution of AI jobs is the evolution direction of the next-generation network. To achieve this goal, we model the job as a directed acyclic graph (DAG), partition it into executors based on the type of task, and minimize the execution time of all jobs in 6G wireless networks by optimizing executors deployment. Considering the dynamic features of channel states and DAG topology, the optimization problem is addressed by deep reinforcement learning, i.e., Deep Q-Network (DQN). In the simulation, we manifest the performance of the DQN-based DAG task scheduling in terms of convergence and latency.

Terahertz communication with abundant spectrum resources is envisioned as the key technology of 6G. Despite its narrow beam, terahertz transmission is still vulnerable to eaves-dropping attacks in indoor scenarios. In this paper, we propose a blockage feature-based artificial noise scheme to safeguard the indoor network in the presence of multiple access points (APs), users, and eavesdroppers. Those APs with blocked links to the typical user are selected to emit artificial noise to deteriorate the reception of eavesdroppers. Thus, communication security is ensured without escalating the instability of legitimate connections caused by the small coverage nature of terahertz beams. By comprehensively considering the propagation characteristics of terahertz, such as the three dimensions narrow beam and the human blocking effect, we derive the theoretical expressions of the connection outage probability, the secrecy outage probability, and the average number of perfect links per unit area. Numerical results demonstrate that the proposed scheme outperforms the traditional schemes in terms of connection stability and secrecy performance.

Massive flood damage has garnered a lot of social attention. Due to the tension between the strong demand for generalized models and the constrained capabilities of edge devices for hydrological surveillance, this study proposes an accessible distributed hydrological surveillance (HS) and computing system with integrated end-edge-cloud (iEEC) architecture to address the issue. In order to increase the inference efficiency of the edge servers (ES), we first develop a HS model with multiple exits, aiming to exploit its network structure and inference strategy. Then, using a collaborative scheduling algorithm, we construct the iEEC pathway to decide whether to undertake edge inference or cloud invocation. With a prototype system and a simulation tool, we eventually performed a numerical analysis of the system at various scales. The accuracy reached 94.3 %, the speed reached 30.3 frames per second (FPS), and it can better handle the occurrence of hard instances compared to state-of-the-art (SOTA) approaches.

High-speed computation resources are provided by mobile edge computing (MEC) to boost various delay-sensitive vehicular applications. However, compared to computing tasks locally, the MEC approach consumes extra energy in the offloading process. In this paper, an asynchronous deep reinforcement learning-based energy-efficient secure offloading (EESO) is proposed to enhance the energy efficiency and security of the vehicular edge computing (VEC) network in the presence of multiple malicious eavesdropper vehicles. To secure the wireless offloading process of the information, a group of jammer vehicles is scheduled to form a NOMA cluster with each user vehicle for providing jamming signals to the eavesdropper vehicles while not interfering with the legitimate user vehicle. We minimize the system energy consumption with the computation delay constraint by jointly optimizing the transmit power, the computation resource allocation, and the selection of jammer vehicles in each NOMA cluster. Then we adopt an asynchronous advantage actor-critic (A3C) learning algorithm to solve the optimization problem. With proper training, the A3C-based EESO scheme can reduce the system energy consumption and improve offloading security.

Millimeter wave (mmWave) technology provides abundant high-capacity channel resources for vehicular communications. However, the mobility of vehicles and the blocking effect of mmWave propagation brings new challenges to communication security. From the perspective of cooperative secure communication, this paper proposes a deep reinforcement learning (DRL)-based joint relay and jammer selection scheme in mmWave vehicular networks. The mmWave base station selects idle vehicles as relay transmission nodes to overcome the severe blocking attenuation of the multi-user downlink legitimate transmissions. Moreover, to ensure secure transmission, a cooperative vehicle is selected to transmit jamming signals to the eavesdropper while the users are not disturbed. We utilize the asynchronous advantage actor-critic (A3C) learning algorithm to optimize the cooperative vehicle selection with the objective of maximizing the total secrecy capacity. Besides, we set the secrecy rate punishment mechanism to guarantee the secrecy performance of each vehicle. We demonstrate that the proposed scheme can rapidly adapt to the highly dynamic vehicular networks and effectively improve secrecy performance.

Despite the high directionality of antennas in terahertz communication, there remains a risk of confidential message interception when eavesdroppers are within the beam coverage area. This paper proposes a blockage-based cooperative jamming scheme to enhance the security of terahertz communication. Due to significant signal attenuation caused by blockages in the terahertz frequency band, we select idle users with blockages between them and the typical user in the indoor three-dimensional (3D) space to act as cooperative jammers. Thus, the jamming signal can deteriorate the reception of eavesdroppers while effectively minimizing interference to the typical user. Taking into account the influence of terahertz channel characteristics, blockage, and 3D antenna model, we derive analytical expression for the secrecy outage probability (SOP). Besides, we analyze the effects of access point (AP) density, blockage density, and user idle factor on network performance. Our results demonstrate that the blockage-based cooperative jamming scheme effectively improves the secrecy performance of the terahertz network.

Abstract Automatic speech recognition (ASR) has been widely used in the field of customer service, but the performance of general ASR in dialect transcription is not satisfactory, especially in Guangdong Province. Targeted training of ASR transcription engine will produce effect, but the training cost is high, and it is not suitable for small‐scale training with multiple dialects and frequencies. The complaint problems in the customer service field have obvious clustering and are suitable for few‐shot and multi‐frequency training. In view of this, in the actual engineering application, the method of ASR transcribed into the dialect error correction thesaurus is tried to be used to replace the wrong words, and have achieved good results. The optimization technology after automatic speech transcription proposed in this study can improve the recognition accuracy of general ASR by 13.75% for dialect words.

With the massive deployment of the Internet of Things (IoT) devices, many data analysis applications emerge for the large amount of data accumulated by IoT. Federated learning (FedL) on IoT devices is an appealing mode to train a precise data analysis model. However, existing FedL schemes either take expensive computation costs (e.g., public-key cryptographic operations) or a large number of interactions among participants. Obviously, these schemes are unsuitable for IoT devices due to the limited computational and communication resources. In this work, we propose a lightweight privacy-preserving FedL scheme for IoT devices. To protect the privacy of individual local data, we add masks to intervening parameters. An effective secret-sharing scheme is adopted to ensure that masks can be eliminated accurately. Considering that FedL involves multiple iterations and mask generation for each iteration costs a large number of interactions among users for privacy guarantee, we also design a secure mask reusing mechanism for large-scale FedL tasks. We prove that our scheme is secure against the honest-but-curious model. In addition, we also expand our scheme to deal with the collusion attack. Extensive experiments on real IoT devices demonstrate the accuracy and efficiency of our work.

With the prosperous development of Internet of Things (IoT), IoT devices have been deployed in various applications, which generates large volume of image data to trace and record the users’ behaviors, resulting in better IoT services. To accurately analyze these huge data to further improve users’ experience on IoT services, deep neural networks (DNNs) are gaining more attention and have become increasingly popular. However, recent studies have shown that DNN models are vulnerable to adversarial attacks, which leads to the risk of applications in practice. Previous works are devoted to extract invariant features from the content circled by edges in images, while such features cannot efficiently deal with the adversarial effect. In this work, we first study this problem from a new angle by exploring the edge feature information, which is intractable to be influenced by adversarial attacks demonstrated by our empirical analysis. Based on this, we propose a novel edge feature-enhanced defense approach called Defed which incorporates edge feature information into denoised network to defend against various adversarial attacks in image area. For the training phase, we only add benign images as the input and exert Gaussian noise to substitute the adversarial attacks to mitigate the dependency of models on specific adversarial attacks. For inference, we design a combination of multiple Defeds trained by different Gaussian noise levels and deploy confidence intervals to judge whether an image is adversarial or not. Experiments over real-world data sets on image classification demonstrate the efficacy and superiority compared to the state-of-the-art defense approaches.

Internet of Things (IoT) applications have penetrated into all aspects of human life. Millions of IoT users and devices, online services, and applications combine to create a complex and heterogeneous network, which complicates the digital identity management. Distributed identity is a promising paradigm to solve IoT identity problems and allows users to have soverignty over their private data. However, the existing state-of-the-art methods are unsuitable for IoT due to continuing issues regarding resource limitations for IoT devices, security and privacy issues, and lack of a systematic proof system. Accordingly, in this article, we propose SmartDID, a novel blockchain-based distributed identity aimed at establishing a self-sovereign identity and providing strong privacy preservation. First, we configure IoT devices as light nodes and design a Sybil-resistant, unlinkable, and supervisable distributed identity that does not rely on central identity providers. We further develop a dual-credential model based on commitment and zero-knowledge proofs to protect the privacy of sensitive attributes, on-chain identity data, and linkage of credentials. Moreover, we combine the basic credential proofs to prove the knowledge of solutions to more complex problems and create a systematic proof system. We go on to provide the security analysis of SmartDID. Experimental analysis shows that our scheme achieves better performance in terms of both credential generation and proof generation when compared with CanDID.

Wireless virtual reality (VR) is expected to be a technology that revolutionizes human interaction and perceived media, where the quality of experience (QoE) is an important indicator to measure user service perception. However, existing schemes only consider general and time-invariant QoE optimization, which may suffer performance degradation. Moreover, it is also necessary to ensure the fairness of the individual user’s performance in wireless VR. To address these challenges, we employ digital twin technology to investigate a max-min QoE-optimal problem for wireless VR systems in this paper. Specifically, we maximize the QoE of the worst-case head-mounted displays (HDMs) client, where the QoE model is the linear weighting combination of video quality, service delay, and energy efficiency. The formulated optimization problem is characterized by multidimensional control, which jointly optimizes model selection, transmit power, computation time, and GPU-cycle frequency. Due to the mixed combinatorial features of the optimization problem, we give a low-complexity algorithm design by decoupling the optimization variables. Notably, we first obtain the allocation of the transmit power by employing the generalized fractional programming theory and the Lagrangian dual decomposition, followed by attaining the optimal allocation of GPU-cycle frequency in VR mode is derived by the proposed adaptive modified harmony search algorithm, and finally achieve the computation time by the barrier method. Meanwhile, we devise a greedy-style heuristic algorithm for mode selection. In the simulation, three baseline schemes are established as comparisons to assess the effectiveness of the proposed scheme. Meanwhile, the simulation results manifest that the proposed algorithms have good convergence performance and better increase the QoE of the DT-enabled wireless VR system compared to benchmark solutions.

The ability to decentralize knowledge graphs (KG) is important to exploit the full potential of the Semantic Web and realize the Web 3.0 vision. However, decentralization also renders KGs more prone to attacks with adverse effects on data integrity and query verifiability. While existing studies focus on ensuring data integrity, how to ensure query verifiability - thus guarding against incorrect, incomplete, or outdated query results - remains unsolved. We propose VeriDKG, the first SPARQL query engine for decentralized knowledge graphs (DKG) that offers both data integrity and query verifiability guarantees. The core of VeriDKG is the RGB-Trie, a new blockchain-maintained authenticated data structure (ADS) facilitating correctness proofs for SPARQL query results. VeriDKG enables verifiability of subqueries by gathering global index information on subgraphs using the RGB-Trie, which is implemented as a new variant of the Merkle prefix tree with an RGB color model. To enable verifiability of the final query result, the RGB-Trie is integrated with a cryptographic accumulator to support verifiable aggregation operations. A rigorous analysis of query verifiability in VeriDKG is presented, along with evidence from an extensive experimental study demonstrating its state-of-the-art query performance on the largeRDFbench benchmark.

Millimeter-wave (mmWave) can provide abundant spectrum resource in vehicular communication networks. Nevertheless, due to the high path-loss and blocking effects in mmWave propagation, and high mobility of vehicles, downlink services for vehicles would be seriously degraded. In this paper, we firstly propose a deep reinforcement learning-based joint beam allocation and relay selection (JoBARS) scheme to mitigate blocking effects and optimize the total transmission rate of the vehicular network, where the mmWave base station (mmBS) provides multi-user services. When downlinks are blocked, the mmBS can select appropriate idle vehicles as relay nodes to enhance service quality from a global perspective. We set the rate punishment restriction in JoBARS scheme to guarantee each vehicle can obtain high-quality service. Besides, a relaying incentive mechanism (RIM) is proposed to avoid vehicles being overly selected for relaying and ensure that relay vehicles have a higher chance of being served in the next round. We demonstrate that JoBARS scheme can effectively enhance the total transmission rate while alleviating transmission outages caused by severe propagation attenuation of mmWave signals. Compared with Greedy Selection scheme, the total rate and average connection probability of vehicles under JoBARS scheme are nearly 17% and 14% higher when blocking effects are severe.

Organizations tend to collaboratively train the deep learning model over their combined datasets for a common benefit (e.g., better-trained model or learning a complicated model). However, due to the consideration about privacy leakage, organizations cannot share their data directly, especially related to sensitive domains. In this paper, a privacy-preserving collaborative deep learning mechanism, namely Sigma, is designed to allow participating organizations to train a collective model without exposing their local training data to the others. Specifically, a single-server-aided private collaborative architecture is introduced to achieve the private collaborative learning, which protects organizations’ data even if$n-1$out of$n$participants colluded. We also design a practical protocol to perform the secure model training, which can resist the typical inference attack through the sharing information. After that, we propose a fair model releasing mechanism for participants and introduce differential privacy to prevent model stealing and membership inference attack. Furthermore, we prove that Sigma can ensure participants’ privacy preservation and analyze the communication overhead in theory. To evaluate the effectiveness and efficiency of Sigma, we conduct an experiment over two real-world datasets and the simulation results demonstrate that Sigma can efficiently achieve the collaborative model training and effectively resist the membership inference attack.

Graph neural networks (GNNs) are a specialized type of deep learning models on graphs by learning aggregations over neighbor nodes. However, recent studies reveal that the performance of GNNs are severely deteriorated by injecting adversarial examples. Hence, improving the robustness of GNNs is of significant importance. Prior works are devoted to reducing the influence of direct adversaries which are adversarial attacks by positioning a node's one-hop neighbors, yet these approaches are limited in protecting GNNs from indirect adversarial attacks within a node's multi-hop neighbors. In this work, we approach this problem from a new angle by exploring the graph Ricci curvature, which can characterize the relationships of both direct and indirect links from any two nodes’ neighborhoods in the Riemannian space. We first investigate the distinguishable properties of adversarial attacks with graph Ricci curvature distribution. Then, a novel defense framework called Cure-GNN is proposed to detect and mitigate adversarial effects. Cure-GNN discerns the distinction between adversarial edges and normal edges via computing curvature, and merges it into the node features reconstructed by a residual learning framework. Extensive experiments over real-world datasets on node classification task demonstrate the efficacy of Cure-GNN and achieves superiority to the state-of-the-arts without incurring high complexity.

Mobile crowdsensing (MCS) systems typically struggle to address the challenge of data aggregation, incentive design, and privacy protection, simultaneously. However, existing solutions usually focus on one or, at most, two of these issues. To this end, this paper presents CROWDFA, a novel paradigm for privacy-preserving MCS through federated analytics (FA), which aims to achieve a well-rounded solution encompassing data aggregation, incentive design, and privacy protection. Specifically, inspired by FA, CRWODFA initiates an MCS computing paradigm that enables data aggregation and incentive design. Participants can perform aggregation operations on their local data, facilitated by CROWDFA, which supports various common data aggregation operations and bidding incentives. To address privacy concerns, CROWDFA relies solely on an efficient cryptographic primitive known as additive secret sharing to simultaneously achieve privacy-preserving data aggregation and privacy-preserving incentive. To instantiate CROWDFA, this paper presents a privacy-preserving data aggregation scheme (PRADA) based on CROWDFA, capable of supporting a range of data aggregation operations. Additionally, a CROWDFA-based privacy-preserving incentive mechanism (PRAED) is designed to ensure truthful and fair incentives for each participant, while maximizing their individual rewards. Theoretical analysis and experimental evaluations demonstrate that CROWDFA protects participants’ data and bid privacy while effectively aggregating sensing data. Notably, CROWDFA outperforms state-of-the-art approaches by achieving up to 22 times faster computation time.

Road hazards (RH) have always been the cause of many serious traffic accidents. These have posed a threat to the safety of drivers, passengers, and pedestrians, and have also resulted in significant losses to people and even to the economies of countries. Hence, road hazards detection (RHD) could play an essential role in intelligent transportation systems (hypertarget ITSITS). The cooperative vehicle-infrastructure systems (CVIS) coordinate the communication between vehicles and roadside infrastructures. Onboard computing devices (OCD), then, make fast analyses and decisions based on road conditions. In this study, an RHD solution based on CVIS is proposed. Firstly, a high-performance heavy action detection model is selected. Using a meta-learning paradigm, critical features are generalized from a few-shot RH data. Secondly, we designed a lightweight RHD model to ensure its smooth inference on an OCD. Thirdly, we use a knowledge distillation (KD) framework to progressively distill the features of the complex model and the privileged information of the data into the lightweight one. Experimental results demonstrate that the model can effectively detect RH and obtain an accuracy of 90.2% with an inference time of 14.7ms.

The mobile edge computing (MEC) technology can simultaneously provide high-speed computing services for multiple vehicular users (VUs) in vehicular edge computing (VEC) networks. Nevertheless, due to the open feature of the wireless offloading channels and the high mobility of the vehicles, the security and stability of the offloading process would be seriously degraded. In this paper, by utilizing the physical layer security (PLS) technique and spectrum sharing architecture, we propose a deep reinforcement learning based joint secure offloading and resource allocation (SORA) scheme to improve the secrecy performance and resource efficiency of the multi-user VEC networks, where the VU offloading links share the frequency spectrum preoccupied with the vehicle-to-vehicle (V2V) communication links. We use Wyner’s wiretap coding scheme to obtain the achievable secrecy rate and guarantee that confidential information cannot be decoded by multiple mobile eavesdroppers. We aim at minimizing the system processing delay while securing the wireless offloading process, by jointly optimizing the transmit power, the frequency spectrum selection and the computation resource allocation. We formulate the optimization problem as a multi-agent collaborative optimal decision problem and solve it with a double deep Q-learning algorithm. Besides, we set a punishment mechanism for the rate degradation to guarantee the communication quality of each V2V link. Simulation results demonstrate that multiple VU agents adopting the SORA scheme can rapidly adapt to the highly dynamic VEC networks and cooperate to improve the system delay performance while increasing the secrecy probability.

Vehicular Edge Computing (VEC) is enjoying a surge in research interest due to the remarkable potential to reduce response delay and alleviate bandwidth pressure. Facing the ever-growing service applications in VEC, how to effectively aggregate and flexibly schedule ubiquitous network resources for implementing diverse tasks and meeting differentiated demands from numerous vehicular users remains haunting. Toward this end, we investigate collaborative task computing and on-demand resource allocation. The collaborative computing framework in VEC is provided to support deep collaboration and intelligent management of heterogeneous resources widely distributed in vehicles, edge servers and cloud. Based on this framework, the joint optimization problem of distributed task offloading and multi-resource management is formulated with the aim to maximize the system utility by making the optimal task and resource scheduling policy, the novelty of which lies in the exploration of available vehicle resources and the consideration of service migration. In view of the dynamics, randomness and time-variant of vehicular networks, the asynchronous deep reinforcement algorithm is leveraged to find the optimal solution. Extensive simulation experiments are implemented to demonstrate the superiority of our proposed algorithm in terms of response latency compared with full offloading and random offloading.

Blockchain has been regarded as a trusted carrier for distributed data storage. With large volumes of valuable data stored on blockchain, data query has become a major requirement. However, the existing blockchains do not provide efficient query functionality because of their deep-rooted chain structure. Blockchain database is a new direction that constructs index on top of blockchain to provide rich query functionalities. The existing works are either insecure because the query process separates from the blockchain consensus, or inscalable because all the data needs to be stored in the block. In this paper, we propose a novel semantic blockchain database called MSTDB. We design a hybrid on/off chain blockchain storage architecture in which the majority of blockchain storage is offloaded to the off-chain storage and a novel index structure named Merkle Semantic Trie (MST) is designed to be a secure and semantic bridge between on- and off-chain. Based on MST, MSTDB provides a variety of semantic query functions including multi-keyword query, range query, Top-K query, and cross-chain query. To improve the performance further, we design some index compression and query preprocessing techniques for MSTDB. Extensive experiments demonstrate the effectiveness and efficiency of our blockchain database.

With the increasing on-board demand for intelligent connected vehicles (ICVs), the fifth-generation (5G) wireless systems are being massively utilized in vehicular networks. As an essential component, content retrieval in the ICV provides a basis for vehicle-to-vehicle or vehicle-to-infrastructure data interaction for many applications. However, content access is still subject to performance degradation due to congested communication channels, diverse requests patterns, and intermittent network connectivity. To mitigate these issues, in-network caching in 5G-enabled ICV has been leveraged to benefit content access by allowing edge nodes to store content for data generators. In this paper, we propose an in-network caching scheme to support various provisions of data sharing in the ICVs by exploring the advantages of information-centric networks (ICN). We first divide each on-board service into several content units. Then, we place these units at the ICV and small cell base stations (SBSs) to reduce the content retrieval delay, further model the proposed system as an integer nonlinear program (INLP) and attain the optimal QoE (Quality of Experience) by placing content units at appropriate cache entities. Finally, we verify the effectiveness and correctness of our proposed model through extensive simulations.

Accurate traffic flow forecasting is crucial to improving traffic safety and alleviating road congestion for intelligent transportation network management. Recently, spatial-temporal graph-based deep learning methods have achieving significant performance improvements in traffic flow forecasting. However, they only consider spatial-temporal correlation of traffic network but ignore a mass of semantic correlation. In addition, they need to centralize data for training models, leading to privacy leakage concern. To tackle these problems, we introduce a federated learning-based intelligent traffic flow forecasting model that integrates our proposed spatial-temporal graph-based deep learning model into the devised Multilevel Federated Learning framework(MFL), named MFVSTGNN. This MFL is used to allow data collaboration among different data owners to train an efficient model without sharing their private data, while achieving the trade-off between communication overhead and computation performance. The proposed spatial-temporal graph-based deep learning model is composed of two phases. The first phase utilizes Variational Graph Autoencoder (VGAE) to dynamically generate adjacency matrix that contains both the spatial and semantic dependencies, contributing to preserving valuable information for improving prediction accuracy, and the second phase employs general spatial-temporal graph neural network to conduct prediction. We evaluate the performance of MFVSTGNN with two large-scale traffic datasets from California and Los Angeles County. The experimental results demonstrate the superior performance of MFVSTGNN in reducing communication overhead, and improving prediction accuracy, validating the effectiveness of our proposed model.

Vehicles are hesitant to upload data to edge servers in vehicle edge computing (VEC) as many vehicle data collected and perceived by various on-board sensors contain sensitive and personal information and lack economic incentive. Instead of free access to shared data, encrypted data trading will alleviate security and privacy concerns and provide an incentive for vehicle owners to share their data. The edge server needs to pay the price in data trading, and reputation management is a great method to help it trade with reliable and available vehicles. In this paper, we propose a multi-armed bandit (MAB)-based reputation management scheme, so the edge servers can select the high reputation vehicles for data trading, which can ensure the credibility and reliability of the data. The encryption scheme is applied to achieve the required transmission security level and defend the rights and interests of the edge server. On the other hand, implementing security measures will consume the computation and communication resources of the vehicles. We formulate an optimization problem that maximizes the revenue of vehicles in data trading under the constraints of time delay, energy consumption, and security level. Simulation results demonstrate that the proposed scheme is effective and efficient for vehicle reputation management, data trading selection, and resource allocation.

Vehicular Edge Computing (VEC) is a promising new paradigm that has attracted much attention in recent years, which can enhance the storage and computing capabilities of vehicular networks to provide users with low latency and high-quality services. Due to the open access and unreliable wireless channels, some appropriate security measures should be implemented in the VEC to ensure information security. However, the operation of the security mechanism dominates supererogatory computing resources, thus affecting the performance of VEC systems. The scarcity of computation and energy resources of the vehicles conflicts with the requirement of tasks for time delay and information security. In this paper, taking the driving velocity and position of the vehicles, the number of lanes, the model and density of the attackers, and security strength into consideration, we formulate a max-min optimization problem to jointly optimize offloading decision, transmit power, task computation frequency, encryption computation frequency, edge computation frequency, and block length to obtain optimal secure information capacity and local computation delay. The formulated optimization problem is a mixed integer nonlinear programming (MINLP), which is intractable. We apply the generalized benders decomposition (GBD)-based method to solve it. The simulation results show that our proposed algorithms have convergence and effectiveness and achieve fairness among vehicles on the road.

A lack of well-designed security solutions within the millimeter-Wave (mmWave) cellular vehicle-to-everything (V2X) communications significantly impedes the development of applications within the intelligent transportation system. Cooperative jamming is envisioned as a potential technology that can enhance physical layer security performance for plane networks by selectively choosing jammers from the perspective of the legitimate receiver. We propose a blockage-and-power-based jammer selection strategy to address potential security pitfalls in a mmWave cellular V2X network. With the help of jammers whose interference power falls within the acceptance range of legitimate receivers, transmission confidentiality is secured simultaneously without escalating the instability of connections caused by the time-varying nature of V2X networks. We derive the theoretical expression of secrecy outage probability and secrecy throughput based on our preliminary analysis of association probability from the stochastic geometry approach. Numerical results demonstrate that the proposed secure transmission scheme outperforms other cooperative jamming schemes in terms of secrecy throughput.

The autonomous vehicle platoon has the potential to cope with the stress caused by the resource-constrained vehicles‘ demand for processing power and the spread-out deployment of MEC-BS. In this poster, we focus on a multi-platoons scenario for task scheduling. Our objective is to minimize the overall energy consumption subject to the long-term latency constraint. To characterize stochastic properties and deal with coupling between variables, we propose a dynamic task scheduling algorithm based on Lyapunov optimization (LDTS). We theoretically and empirically evaluate the performance of the proposed algorithm, which is illustrated to be significantly better than state-of-the-art and other benchmark approaches in terms of execution latency and energy consumption.

The full-duplex millimeter-wave communication has drawn significant attention for its rich spectrum resources and high spectrum efficiency characteristics. However, due to the information leakage during transmission, secure threats in the full-duplex systems still exist. In this paper, we propose a full-duplex jamming based secure transmission scheme, where the instantaneous channel state information of eavesdropping channel is unknown. We study the optimal design of hybrid beamforming and power allocation jointly with secrecy outage probability constraint. Our results reveal that joint optimization highly facilitates the secrecy performance of full-duplex mmWave communication, without any self-interference limitations in the multiple-antenna scenarios.

As Internet of Things (IoT) is more and more pervasive and deployed in critical applications, it's becoming increasingly important to preserve the confidentiality of sensitive data when IoT devices communicate with each other. However, traditional cryptography is usually time and energy consuming. It may not be applicable to IoT devices with limited computational capability or limited power. In this paper, we propose a lightweight encryption scheme named Dynamic Wireless Channel P ad (DyWCP) inspired by one-time pad encryption. One-time pad encryption achieves perfect secrecy but has been rarely used in practice due to the inconvenience of key negotiation. Our research discovers that in the wireless context it is possible to design a one-time pad encryption scheme without key negotiation. Towards the realization of DyWCP, we create techniques to utilize the additive feature of wireless channel to encrypt messages, to integrate modular operations at wireless physical layer, and to defend against multiple eavesdroppers. We implement a prototype of the proposed scheme using Universal Software Defined Radio Peripherals (USRP), and conduct a suite of experiments to evaluate the performance of the proposed scheme.

With the transmission and sharing of data in the Internet of Things (IoT), while bringing development to life and the economy, it also inevitably threatens the data copyright protection and authentication. Digital watermarking technology can provide an effective solution for copyright protection by embedding the watermark in the data to prove the copyright attribution. The existing methods of digital watermarking in IoT mainly target multimedia, without considering the copyright authentication in database data. Unlike multimedia information, the database does not focus on the subjective visual perception when using the data, but rather on the potential values unlocked from the data through algorithms such as data mining. Therefore, we propose a new database watermarking algorithm based on decision tree shift correction (DTSC), considering the data copyright authentication and usability when applying for data mining algorithm. The algorithm adjusts the watermarked data by the DTSC method and makes the watermarked decision tree identical to the original in the iteration process. It solves the problem of database data copyright authentication in IoT and ensures the usability of the data when used for decision tree model construction. From the simulation results, it can be seen that the proposed method ensures the usability of the data for the classification and regression tree decision tree algorithm while embedding the watermark in the database data, and the data distortion of the proposed method does not differ from that of the traditional watermarking algorithm.

Cloud storage and edge computing provide the possibility to address the tremendous storage and computing pressure caused by the explosive growth of traffic at the edge of the networks. In this scene, as data is outsourced to the cloud or edge servers, data privacy can be leaked. For enhancing security and privacy, attribute-based searchable encryption (ABSE), as an effective technical approach, achieves controllable search of ciphertext. Aiming at addressing the issues of the low search efficiency in a single-keyword ABSE scheme and the large computing overhead of the existing multikeyword ABSE schemes, we propose a novel multikeyword ABSE scheme (EMK-ABSE) through cloud-edge coordination. The huge amounts of encrypted data is stored to cloud server (CS), while the corresponding encrypted index is uploaded to the nearest edge node (EN) to perform multikeyword search and assisted decryption. To further release the computational burden of clients, a hybrid online/offline mechanism is adopted in encryption. Security analysis indicates that the multikeyword index in EMK-ABSE has secure indistinguishability under chosen keyword attack (IND-CKA). The comprehensive evaluation proves that EMK-ABSE achieves not only encrypted multikeyword retrieval but also fine-grained access control, with lower computation complexity in the three stages of encryption, trapdoor generation, and decryption. We show that the proposed scheme has higher efficiency and practicability than the selected relative works.

Millimeter wave (Mmwave) communication can realize high rate service for the upcoming Internet of Things (IoT) networks. Although directional multiantenna gains can help enhance security, randomly distributed eavesdroppers can still intercept confidential messages by residing in both the main-lobe and side-lobe areas of the beam signal. Considering the unique propagation features of mmWave, this article explores the potential of physical layer security in mmWave multiple-input–multiple-output (MIMO) systems. We propose an artificial noise (AN)-aided capacity threshold on–off secure transmission scheme to resist the eavesdropping threat. Taking into account the influence of mmWave channel characteristics, random blockage, and multiantenna gains, we first derive the closed-form expressions of transmission probability (TP) and secrecy outage probability (SOP) in a noncolluding eavesdropping scenario. Then, the lower bound of SOP with AN and closed-form expression of SOP without AN is derived in a colluding eavesdropping scenario. Theoretical analysis evaluates the impacts of various system parameters on secrecy performance and verifies the effects of AN interference on inhibiting side-lobe eavesdropping. Simulation results validate the theoretical results and indicate that the combination of capacity threshold on–off transmission scheme, AN interference, and multiantenna directional gains can effectively reduce the security threats of mmWave MIMO systems. Besides, the optimal power allocation ratio of AN in noncolluding scenarios is demonstrated and its rule is summarized, which depends on whether legitimate communication links are in blockage.

Edge computing brings computation and storage resources to the edge of the mobile network to meet strict delay and high demanding applications. However, edge network environments are more vulnerable to malicious attacks. Reliable communication in networks usually relies heavily on verifying the authentication of content and identity. Nevertheless, enhancing the authentication security level means occupying more computation resources, time, and energy. There is a tradeoff between security level improvement and resource optimization in computation offloading. In this article, we take maximizing the authentication security level of the Merkle tree signature as segmental of the optimization objective and consider the different hash algorithms deployed on the edge servers to make the offloading decision. Specifically, to weight the time delay and authentication security level simultaneously, we formulate a minimum optimization problem to jointly optimize the offloading decision, packet transmitting rate, edge computation frequency, and data blocks number. Simulation results show that our proposed algorithms have well convergence and effectiveness and provide a tradeoff between time delay and authentication security level.

Edge infrastructures, including edge computing servers, are increasingly powered by renewable energy and smart grid combined. Two-way energy trading allows the surplus or shortfall of renewable energy to be traded between a server and the smart grid, but is non-trivial due to randomly varying computation demands and renewables. This paper proposes a new online policy, namely, distributed online resource allocation and load management (DORL), which enables such an edge server and its serving devices to minimize their energy cost and energy consumption, respectively, in a fully distributed manner. The key idea is that we employ the stochastic dual-subgradient method to interpret the battery of the server as a virtual queue. Based on the virtual queue and task queues, the CPU frequencies of the devices and the edge server, the offloading transmit rates of the devices (to the server) and the energy trading decisions of the server (with the smart grid) are decoupled over time and among devices, and optimized on an ongoing basis. Furthermore, we prove that the DORL yields a feasible and asymptotically optimal solution with a cost-backlog tradeoff of$[\eta, 1/\eta]$. Simulations show that the DORL reduces the system cost by nearly 50%, as compared to existing benchmarks.

Federated learning (FL) is a popular edge learning approach that utilizes local data and computing resources of network edge devices to train machine learning (ML) models while preserving users’ privacy. Nevertheless, performing efficient learning tasks on the devices and achieving longer battery life are primary challenges faced by federated learning. In this paper, we are the first to study the application of heterogeneous computing (HC) and wireless power transfer (WPT) to federated learning to address these challenges. Especially, we propose a heterogeneous computation and resource allocation framework based on a heterogeneous mobile architecture to achieve effective implementation of FL. To minimize the energy consumption of smart devices and maximize their harvesting energy simultaneously, we formulate an optimization problem featuring multidimensional control, which jointly considers time splitting for WPT, dataset size allocation, transmit power allocation and subcarrier assignment during communications, and processor frequency of processing units (central processing unit (CPU) and graphics processing unit (GPU)). However, the major obstacle is how to design a proper algorithm to solve this optimization problem efficiently. For this purpose, we decouple the optimization variables so as to achieve high efficiency in deriving its solution. Particularly, we first compute the optimal processor frequency and dataset size allocation via employing the Lagrangian dual method, followed by finding the closed-form solution to the optimal time splitting allocation, and finally attain the optimal subcarrier assignment as well as transmit power for transmissions through an iteration algorithm. To evaluate the performance of our proposed scheme, we set up four baseline schemes as comparison, and simulation results show that the proposed scheme converges quite fast and better enhance the energy efficiency of the wireless powered FL system compared with the baseline schemes.

Privacy concerns of using sensitive biometric data as credentials arise with the wide adoption of user-friendly face authentication. To protect the facial features of users, two important functions, i.e.,revocabilityandreusability, are anticipated to be realized in a privacy-preserving face authentication design. Revocability requires an effective approach to deregister or replace user credentials when the authentication server is compromised; For reusability, the same credentials should appear independently to non-cooperating applications. Accomplishing these two properties is challenging as the uniqueness of facial features. In this article, we presentPrivFace, a fast privacy-preserving face authentication, supporting revocable, and reusable biometric credentials. The core innovation is a novel secure inner product protocol that employs a lightweight random masking technique instead of time-consuming public-key cryptographic operations to efficiently measure facial data similarity. We rigorously analyze the security to show that the server cannot acquire the user's sensitive biological features during the authentication. Our experiment with real-world datasets shows thatPrivFaceis friendly to edge smart devices, which takes less than$100 ms$per successful authentication on a common smartphone and outperforms the prior art J. Lei, Q. Peiet al.[1]. by$20 \times$. We have made the relevant codes open-source to the community for further research.

The rapid development of the smart healthcare system makes the early-stage detection of dementia disease more user-friendly and affordable. However, the main concern is the potential serious privacy leakage of the system. In this article, we take Alzheimer's disease (AD) as an example and design a convenient and privacy-preserving system namedADDetectorwith the assistance of Internet of Things (IoT) devices and security mechanisms. Particularly, to achieve effective AD detection,ADDetectoronly collects user's audio by IoT devices widely deployed in the smart home environment and utilizes novel topic-based linguistic features to improve the detection accuracy. For the privacy breach existing in data, feature, and model levels,ADDetectorachieves privacy-preserving by employing a unique three-layer (i.e., user, client, cloud, etc.) architecture. Moreover,ADDetectorexploitsfederated learning (FL) based schemeto ensure the user owns the integrity of raw data and secure the confidentiality of the classification model and implementdifferential privacy (DP) mechanismto enhance the privacy level of the feature. Furthermore, to secure the model aggregation process between clients and cloud in FL-based scheme, a novelasynchronous privacy-preserving aggregation frameworkis designed. We evaluateADDetectoron 1010 AD detection trials from 99 health and AD users. The experimental results show thatADDetectorachieves high accuracy of 81.9% and low time overhead of 0.7 s when implementing all privacy-preserving mechanisms (i.e., FL, DP, and cryptography-based aggregation).

Considering the high mobility and uneven distribution of vehicles, an efficient routing protocol should avoid that the sent packets are forwarded within road segments with ultra-low density or serious data congestion in vehicular networks. To this end, in this paper, we propose a Traffic aware and Link Quality sensitive Routing Protocol (TLRP) for urban Internet of Vehicles (IoV). First, we design a novel routing metric, i.e., Link Transmission Quality (LTQ), to account for the impact of the number, quality and relative positions of communication links along a routing path on the network performance. Then, to adapt to the dynamic characteristics of IoV, a road weight evaluation scheme is presented to assess each road segment using the real-time traffic and link information quantified by the LTQ. Next, the path with the lowest aggregated weight is selected as the routing candidate. Extensive simulations demonstrate that our proposed protocol achieves significant performance improvements compared to the state-of-the-art protocol MM-GPSR, the typical junction-based scheme E-GyTAR, and the classic connectivity-based routing iCAR, in terms of packet delivery ratio and average transmission delay.

Recent studies have demonstrated the potentials of federated learning (FL) in achieving cooperative and privacy-preserving data analytics. It would also be promising if FL can be employed in vehicular ad hoc networks (VANETs) for cooperative learning tasks, such as steering angle prediction, trajectory prediction, drivable road detection, etc., among integrated vehicles. However, since VANETs are characterized by ad hoc cooperating vehicles with non-independent and identically distributed (Non-IID) data, directly employing existing FL frameworks to VANETs may cause extensive communication overhead and compromised model performance. Further, most of the existing deep learning models incorporated in FL frameworks rely heavily on data with manual annotations, leading to a huge labor cost. To address these issues, in this paper we propose an efficient and effective Federated End-to-End Learning framework for cooperative learning tasks in VANETs, named FEEL. Specifically, we first formulate a distributed optimization problem for cooperative deep learning tasks with Non-IID data in multi-hop cluster VANETs. Second, two algorithms for inter-cluster learning and inner-cluster learning are respectively designed, to reduce the communication overhead and fit Non-IID data. Third, a Paillier-based communication protocol is crafted, allowing secure model parameter updates at the central server without knowing the real updates at each cooperating base station. Extensive experiments on two real-world datasets are conducted by considering various data distributions and VANET topologies, demonstrating the high efficiency and effectiveness of the proposed FEEL framework in both regression and classification tasks.

In recent years, vehicular named data networking (VNDN) has quickly ascended to the spotlight and gained enormous popularity, which has emerged as a candidate to support various applications of vehicular communications. VNDN has the potential improve the data dissemination efficiency by mitigating the performance degradation from Internet Protocol (IP) addressing, unstable connectivity and diversified service requirements. With the number of connected vehicles increasing rapidly, the traffic burden of the base station (BS) also grows. As an effective edge computing paradigm, in-vehicle caching can significantly relieve the pressure of the BS. However, the design of a fair caching strategy is still challenging due to the selfish nature of individuals. In this paper, to address the above issues, a popularity-incentive caching scheme (PICS) is proposed in VNDN, where the BS will reward vehicles who execute cache offloading and content sharing with others. To balance the conflict of interest between the BS and vehicles, a Stackelberg game is modeled with rational utilities envisioned. Next, we propose the solution of this game model and evaluate the influence of different weight parameters. Finally, simulation results validate the effectiveness of PICS.

The rapid advancement of intelligent vehicles is deemed crucial to the emergence of diverse compute-intensive applications of assisted driving, which consist of automatic driving, speed recognition, hybrid sensing data fusion, etc. Nevertheless, resources-constraint vehicles with high mobility cannot always meet the computing and communication demands when the above applications occur. Additionally, considering the expensive and inflexible deployment of edge servers, offloading application tasks to “Edge” in the vehicular networks is not always working well. To effectively mitigate the above issues, the complicated application tasks are motivated to offload to the vehicle platoon, where the vehicles travel synchronously in a string with small headway. Benefiting from the stable connectivity, adjustable mobility, and reasonable charge, the task vehicle would like to process the task by leveraging the idle resources of each platoon member (PM). To make more effective use of the resources on the mobile edge platoon cloud (MEPC), we investigate the resource allocation strategy based on the task vehicle’s service pricing strategy in this work. We first formulate the interactions between MEPC and task vehicle as a Stackelberg game to study the joint utility maximization of the MEPC and task vehicle. Then the Stackelberg Equilibrium (SE) for the proposed game is characterized and proved. The proposed algorithm Hook-Jeeves-based Stackelberg game (HJSG) can reach the SE. Finally, we introduce the consortium blockchain to ensure the security and privacy of service transactions. The entire system helps enhance task processing efficiency, protect transaction data, and improve service experience. Experimental results over numerical simulation based on practical scenarios demonstrate that compared with Multi-round Stackelberg Game (MRSG), uniform pricing, and the local computation strategy, the proposed HJSG algorithm can attain less execution time and faster convergence performance.

As a distributed deep learning paradigm, federated learning (FL) provides a powerful tool for the accurate and efficient processing of on-board data in vehicular edge computing (VEC). However, FL involves the training and transmission of model parameters, which consumes the vehicles’ precious energy resources and takes up much time. It is a departure from many applications with severe real-time requirements in VEC. And the capabilities and data quality of each vehicle are distinct that will affect the performance of training the model. Therefore, it is crucial to select the appropriate vehicles to participate in learning tasks and optimize resource allocation under learning time and energy consumption constraints. In this paper, taking the vehicle position and velocity into consideration, we formulate a min-max optimization problem to jointly optimize the on-board computation capability, transmission power, and local model accuracy to achieve the minimum cost in the worst case of FL. Specifically, we propose a greedy algorithm to select vehicles with higher image quality dynamically, and it keeps the system’s overall cost to a minimum in FL. The formulated optimization problem is a nonlinear programming problem, so we decompose it into two subproblems. For the resource allocation problem, we use the Lagrangian dual problem and the subgradient projection method to approximate the optimal value iteratively. For the local model accuracy problem, we develop an adaptive harmony algorithm for heuristic search. The simulation results show that our proposed algorithms have well convergence and effectiveness and achieve a tradeoff between cost and fairness.

As a key use case of Industry 4.0 and the Smart City, the Internet of Vehicles (IoV) provides an efficient way for city managers to regulate the traffic flow, improve the commuting performance, reduce the transportation facility cost, alleviate the traffic jam, and so on. In fact, the significant development of Internet of Vehicles has boosted the emergence of a variety of Industry 4.0 applications, e.g., smart logistics, intelligent transforation, and autonomous driving. The prerequisite of deploying these applications is the design of efficient data dissemination schemes by which the interactive information could be effectively exchanged. However, in Internet of Vehicles, an efficient data scheme should adapt to the high node movement and frequent network changing. To achieve the objective, the ability to predict short-term traffic is crucial for making optimal policy in advance. In this article, we propose a novel data dissemination scheme by exploring short-term traffic prediction for Industry 4.0 applications enabled in Internet of Vehicles. First, we present a three-tier network architecture with the aim to simply network management and reduce communication overheads. To capture dynamic network changing, a deep learning network is employed by the controller in this architecture to predict short-term traffic with the availability of enormous traffic data. Based on the traffic prediction, each road segment can be assigned a weight through the built two-dimensional delay model, enabling the controller to make routing decisions in advance. With the global weight information, the controller leverages the ant colony optimization algorithm to find the optimal routing path with minimum delay. Extensive simulations are carried out to demonstrate the accuracy of the traffic prediction model and the superiority of the proposed data dissemination scheme for Industry 4.0 applications.

Federated learning is a distributed machine learning technology that can protect users’ data privacy, so it has attracted more and more attention in the industry and academia. Nonetheless, most of the existing works focused on the cost optimization of the entire process, while the cost of individual participants cannot be considered. In this article, we explore a min-max cost-optimal problem to guarantee the convergence rate of federated learning in terms of cost in wireless edge networks. In particular, we minimize the cost of the worst-case participant subject to the delay, local CPU-cycle frequency, power allocation, local accuracy, and subcarrier assignment constraints. Considering that the formulated problem is a mixed-integer nonlinear programming problem, we decompose it into several sub-problems to derive its solutions, in which the subcarrier assignment and power allocation are obtained by utilizing the Lagrangian dual decomposition method, the CPU-cycle frequency is obtained by a heuristic algorithm, and the local accuracy is obtained by an iteration algorithm. Simulation results show the convergence of the proposed algorithm and reveal that the proposed scheme can accomplish a tradeoff between the cost and fairness by comparing the proposed scheme with the existing schemes.

With the rapid development of intelligent transportation, various computation-intensive applications have e-merged to improve the safety, efficiency, and comfort on the road. However, due to the mobility and resource dynamics, it is still a challenge for the resource-constrained vehicles to timely process computation-intensive tasks. Fortunately, the computation offloading in the Internet of Vehicles (IoV) greatly eases the contradiction between resource constraints and computing requirements. In this paper, we first present a collaborative computing architecture based on Edge-Cloud (EC) and Mobile-Edge-Platooning-Cloud (MEPC). Then, considering the priority of the Delay-Sensitive Tasks (DSTs), preemptive scheduling is introduced to deal with the hybrid tasks, comprised of DSTs and Delay-Tolerant Tasks (DTTs). Finally, a computation offloading problem based on the collaborative EC-MEPC architecture is established by jointly optimizing the decision-making and resource allocation issue. To solve the above problem, a distributed computation offloading and resource allocation algorithm is designed to achieve the optimal solution. Simulation results show that the proposed collaborative computing architecture and the distributed algorithm can effectively improve the delay and energy consumption performance of this system.

Edge computing is a promising paradigm that pushes computing, storage, and energy to the networks' edge. It utilizes the data nearby the users to provide real-time, energy-efficient, and reliable services. Neural network inference in edge computing is a powerful tool for various applications. However, edge server will collect more personal sensitive information of users inevitably. It is the most basic requirement for users to ensure their security and privacy while obtaining accurate inference results. Homomorphic encryption (HE) technology is confidential computing that directly performs mathematical computing on encrypted data. But it only can carry out limited addition and multiplication operation with very low efficiency. Intel software guard extension (SGX) can provide a trusted isolation space in the CPU to ensure the confidentiality and integrity of code and data executed. But several defects are hard to overcome due to hardware design limitations when applying SGX in inference services. This paper proposes a hybrid framework utilizing SGX to accelerate the HE-based convolutional neural network (CNN) inference, eliminating the approximation operations in HE to improve inference accuracy in theory. Besides, SGX is also taken as a built-in trusted third party to distribute keys, thereby improving our framework's scalability and flexibility. We have quantified the various CNN operations in the respective cases of HE and SGX to provide the foresight practice. Taking the connected and autonomous vehicles as a case study in edge computing, we implemented this hybrid framework in CNN to verify its feasibility and advantage.

Millimeter-wave(Mmwave) networks with high directional antennas have enhanced security. However, eavesdroppers can still intercept confidential messages by residing in both signal main-lobe and side-lobe areas. This paper investigates the secrecy performance of artificial-noise (AN)-aided transmission in mmWave systems under the capacity-threshold on-off scheme in the presence of randomly distributed eavesdroppers, which utilizes AN to resist eavesdroppers in the side-lobe area. Considering the effects of mmWave channel characteristics, blockages, and directional antenna arrays, we derive the transmission probability (TP) and closed-form expression of secrecy outage probability (SOP) in the non-colluding eavesdropping scenario. What's more, we derive the analytical expression of SOP in the colluding eavesdropping scenario and its lower bound. Specifically, we characterize the impacts of various system parameters on the secrecy performance and verify the contribution of AN-jamming to inhibiting side-lobe information leakage, meanwhile, the optimal power allocation of AN is analyzed in non-colluding scenarios. Besides, our results reveal that with the narrower main beam and higher antenna gain, the secrecy performance is enhanced significantly. The analytical and numerical results show that the capacity-based transmission scheme with AN-jamming can effectively improve the secrecy performance of mmWave systems.

Mobile-edge computing (MEC) is a promising technology, which allows reducing latency and energy consumption, thereby making the user experience better. Although MEC can support various types of services, differentiated Quality-of-Service (QoS) requirements bring difficulties and challenges to the allocation of radio resources and computing resources of the MEC system. In this article, we jointly optimize subchannel allocation, as well as the local central processing unit (CPU) speed scaling, user association, subcarrier assignment, power allocation, and video quality decision for MEC systems to study the total cost saving problem. Considering the traffic variations, we develop an online algorithm by using the Lyapunov optimization technique to solve this problem, referred to as dynamic subchannel allocation and resource allocation (DSARA). Particularly, the proposed DSARA algorithm only needs to track the state of the current network without requiring any prior knowledge. Besides, we prove that our proposed algorithm can asymptotically achieve the minimum total cost value (such as minimizing the power consumption and maximizing quality satisfaction). Simulation results show that the DSARA can achieve a good tradeoff between the total cost and delay, and outperforms the existing schemes in terms of the total cost expenditure.

Mobile-edge computing (MEC) plays a significant role in enabling diverse service applications by implementing efficient data sharing. However, the unique characteristics of MEC also bring data privacy and security problem, which impedes the development of MEC. Blockchain is viewed as a promising technology to guarantee the security and traceability of data sharing. Nonetheless, how to integrate blockchain into MEC system is quite challenging because of dynamic characteristics of channel conditions and network loads. To this end, we propose a secure data sharing scheme in the blockchain-enabled MEC system using an asynchronous learning approach in this article. First, a blockchain-enabled secure data sharing framework in the MEC system is presented. Then, we present an adaptive privacy-preserving mechanism according to available system resources and privacy demands of users. Next, an optimization problem of secure data sharing is formulated in the blockchain-enabled MEC system with the aim to maximize the system performance with respect to the decreased energy consumption of MEC system and the increased throughput of blockchain system. Especially, an asynchronous learning approach is employed to solve the formulated problem. The numerical results demonstrate the superiority of our proposed secure data sharing scheme when compared with some popular benchmark algorithms in terms of average throughput, average energy consumption, and reward.

As an important driving factor of emerging Internet-of-Things (IoT) applications, machine learning algorithms are currently facing the challenge of how to “clean” data noise, that is introduced during the training process (e.g., asynchronous execution and lossy data compression and quantization). In an attempt to guarantee data quality, various data cleaning approaches have been proposed to filter out abnormal data entries based on the global data distribution. However, most existing data cleaning approaches are based on a centralized paradigm and thus cannot be applied to future edge-based IoT applications, where each edge node (EN) has only a limited view of the global data distribution. Moreover, the increasing demand for privacy preservation largely prevents ENs from combining their data for centralized cleaning. In this study, we propose a federated data cleaning protocol, coined as FedClean, for edge intelligence (EI) scenarios that is designed to achieve data cleaning without compromising data privacy. More specifically, different ENs first generate Boolean shares of their data and distribute them to two noncolluding servers. These two servers then run the FedClean protocol to privately and efficiently compute the attribute value frequency (AVF) scores of the collected data entries, which are then sorted in ascending order via a bitonic sorting network without revealing their values. As a result, data entries with lower AVF scores are considered as abnormal and filtered out. The security, efficiency, and effectiveness of the proposed approach are then demonstrated via concrete security analysis and comprehensive experiments.

The dynamics of cerebellar neuronal networks is controlled by the underlying building blocks of neurons and synapses between them. For which, the computation of Purkinje cells (PCs), the only output cells of the cerebellar cortex, is implemented through various types of neural pathways interactively routing excitation and inhibition converged to PCs. Such tuning of excitation and inhibition, coming from the gating of specific pathways as well as short-term plasticity (STP) of the synapses, plays a dominant role in controlling the PC dynamics in terms of firing rate and spike timing. PCs receive cascade feedforward inputs from two major neural pathways: the first one is the feedforward excitatory pathway from granule cells (GCs) to PCs; the second one is the feedforward inhibition pathway from GCs, via molecular layer interneurons (MLIs), to PCs. The GC-PC pathway, together with short-term dynamics of excitatory synapses, has been a focus over past decades, whereas recent experimental evidence shows that MLIs also greatly contribute to controlling PC activity. Therefore, it is expected that the diversity of excitation gated by STP of GC-PC synapses, modulated by strong inhibition from MLI-PC synapses, can promote the computation performed by PCs. However, it remains unclear how these two neural pathways are interacted to modulate PC dynamics. Here using a computational model of PC network installed with these two neural pathways, we addressed this question to investigate the change of PC firing dynamics at the level of single cell and network. We show that the nonlinear characteristics of excitatory STP dynamics can significantly modulate PC spiking dynamics mediated by inhibition. The changes in PC firing rate, firing phase, and temporal spike pattern, are strongly modulated by these two factors in different ways. MLIs mainly contribute to variable delays in the postsynaptic action potentials of PCs while modulated by excitation STP. Notably, the diversity of synchronization and pause response in the PC network is governed not only by the balance of excitation and inhibition, but also by the synaptic STP, depending on input burst patterns. Especially, the pause response shown in the PC network can only emerge with the interaction of both pathways. Together with other recent findings, our results show that the interaction of feedforward pathways of excitation and inhibition, incorporated with synaptic short-term dynamics, can dramatically regulate the PC activities that consequently change the network dynamics of the cerebellar circuit.

Abstract Online taxi-hailing has become people’s most popular trip mode due to its convenience and low cost. However, it also poses a privacy threat to passengers and drivers, since the online taxi-hailing service providers are able to track their precise mobility trajectories. In addition, there is a certain time delay between the time of a passenger makes a request and the time of the driver arrives the passenger’s boarding position in current online taxi-hailing system. To solve these two problems, we present a new and efficient location privacy protection scheme based on the MinHash algorithm (LPPM). With the LPPM, the exact positions of passengers and drivers are generalized into a set of points of interest around them, and the distance between them is transformed into the similarity between the two sets. Thus a service provider can efficiently match passengers and drivers by using MinHash algorithm without revealing their specific location information. In this paper, we use mobile edge computing technology in the online taxi-hailing system to address the second challenge. It can speed up data processing, drivers can make decisions in advance and reduce the possibility of road congestion. Security analysis shows that LPPM has high security, and the final experimental results confirmed that LPPM is effective.

An intelligent transportation system (ITS) plays an important role in public transport management, security and other issues. Traffic flow detection is an important part of the ITS. Based on the real-time acquisition of urban road traffic flow information, an ITS provides intelligent guidance for relieving traffic jams and reducing environmental pollution. The traffic flow detection in an ITS usually adopts the cloud computing mode. The edge of the network will transmit all the captured video to the cloud computing center. However, the increasing traffic monitoring has brought great challenges to the storage, communication and processing of traditional transportation systems based on cloud computing. To address this issue, a traffic flow detection scheme based on deep learning on the edge node is proposed in this article. First, we propose a vehicle detection algorithm based on the YOLOv3 (You Only Look Once) model trained with a great volume of traffic data. We pruned the model to ensure its efficiency on the edge equipment. After that, the DeepSORT (Deep Simple Online and Realtime Tracking) algorithm is optimized by retraining the feature extractor for multiobject vehicle tracking. Then, we propose a real-time vehicle tracking counter for vehicles that combines the vehicle detection and vehicle tracking algorithms to realize the detection of traffic flow. Finally, the vehicle detection network and multiple-object tracking network are migrated and deployed on the edge device Jetson TX2 platform, and we verify the correctness and efficiency of our framework. The test results indicate that our model can efficiently detect the traffic flow with an average processing speed of 37.9 FPS (frames per second) and an average accuracy of 92.0% on the edge device.

In Internet of Vehicles (IoV), accurate traffic flow prediction is helpful for analyzing road condition and then timely feedback traffic information to managers as well as travelers. Traditional traffic flow predictions are generally suffering from the performance degradation by over-fitting and manual intervening, which cannot support large-scale and high-dimensional urban road network data. To address this issue, in this paper, a traffic flow prediction framework for urban road network based on deep learning is proposed. Firstly, the feature engineering is introduced to extract the features from a large volume of traffic dataset, with the anomaly nodes eliminated. Next, the big traffic dataset is compressed through the spectral clustering compression scheme. Finally, we designed a hybrid traffic flow prediction scheme based on LSTM (Long Short Term Memory) and Sparse Auto-Encoder (SAE). Experimental results show that our proposed model is superior to other models with an average prediction accuracy approaching 97.7%.

Information-centric networking (ICN) as an emerging networking paradigm has recently gained significant attention, due to the improvement of content delivery efficiency. The built-in network storage for caching is a key component in ICN to provide low latency service and reduce high backhaul traffic by caching popular content. However, users' content preference contains individual sensitive characteristics which is distinguishable from others. Therefore, in this work, we propose a data-driven caching revenue maximization problem with the considerations of users' local differential privacy. Specifically, we employ dBitFlip, a local differential privacy (LDP) mechanism, to locally add differential private noise to the users' preference content information. We leverage data-driven approach to predict the content popularity based on the reference distribution constructed by the reported noisy preference content data from users, mathematically present the distance between the noisy reference distribution and the true distribution by the tolerance level, and prove the relationship among the tolerance level, differential privacy budget and the confidence level. We provide feasible solutions to the proposed revenue maximization problem, and conduct simulations to show the effectiveness of the proposed scheme.

Machine learning has a vast outreach in principal applications and uses large amount of data to train the models, prompting a viable and easy to use Machine Learning as a Service (MLaaS). This flexible paradigm however, could have immense privacy implications since the training data often contains sensitive features, and adversarial access to such models could pose a security risk. In adversarial attacks such as model inversion attack on a system used for face recognition, an adversary uses the output (target label) to reconstruct the input (image of the target individual from the training dataset). To avert such a vulnerability of the system, in this paper, we develop a novel approach of applying perceptual hash to parts of the given training images that leverages the functional mechanism of image hashing. The facial recognition system is then trained over this newly created dataset of perceptually hashed images and high classification accuracy is observed. Furthermore, we demonstrate a series of model inversion attacks emulating adversarial access that yield hashed images of target individuals instead of the original training dataset images; thereby preventing original image reconstruction and counteracting the inversion attack. Through rigorous empirical evaluations of applying the proposed formulation over real world dataset, we verify the effectiveness of our proposed framework in protecting the training image dataset and counteracting inversion attack.

To provide intelligent and personalized services on smart devices, machine learning techniques have been widely used to learn from data, identify patterns, and make automated decisions. Machine learning processes typically require a large amount of representative data that are often collected through crowdsourcing from end users. However, user data could be sensitive in nature, and learning machine learning models on these data may expose sensitive information of users, violating their privacy. Moreover, to meet the increasing demand of personalized services, these learned models should capture their individual characteristics. This paper proposes a privacy-preserving approach for learning effective personalized models on distributed user data while guaranteeing the differential privacy of user data. Practical issues in a distributed learning system such as user heterogeneity are considered in the proposed approach. Moreover, the convergence property and privacy guarantee of the proposed approach are rigorously analyzed. Experiments on realistic mobile sensing data demonstrate that the proposed approach is robust to high user heterogeneity and offer a trade-off between accuracy and privacy.

Internet of Vehicles (IoV) have been attracting increasing interests in recent years, targeting to support services between vehicles or vehicles and infrastructures involving driving safety, traffic and infotainment. However, the dynamic nature of IoV make it quite challenging by applying traditional TCP/IP protocol stack, considering the complex signaling and addressing procedure of TCP/IP as well as the strict End-to-End service requirements in vehicular environment. To address these issues, an information centric data dissemination scheme (IDDS) in IoV is proposed. At first, the framework of our IDDS is introduced with the PDU (Protocol Data Unit) type, data structure and protocol signaling procedure given. After that, to increase the data delivery ratio and reduce the incurred latency, a defer time based forwarder selection scheme is presented, with which the “Interest” and “Reply” packets could be exchanged on the link with better transmission performance, thus mitigating the negative impact of high mobility of vehicles. Simulation results show that IDDS could outperforms some traditional strategies in terms of average hop count and content acquisition delay, thus significantly increasing the data dissemination efficiency in vehicular information-centric networks.

In the era of information exploration, collaborative filtering algorithms have been widely adopted to offer useful contents according the different preferences of the users. Unfortunately, due to the sparsity of the original rating data, different data owners are highly motivated to collaborate with each other to guarantee the prediction accuracy via CF algorithms. However, as the original rating data contains sensitive information of the users, strict privacy preserving requirements might hinder the collaboration of different data owners. Although there exist some works to address the privacy issues in CF, they do not consider the cases where the CF algorithms are executed based the integration of multiple datasets. Thus in this paper, we propose a privacy-preserving multiparty scheme for collaborative filtering, using mixed MPC protocols combined with Yao garbled circuit and additive secret sharing. And the accuracy and efficiency of the proposed scheme is verified under the real dataset.

Cross-heterogeneous blockchain interactions have been attracting much attention due to their application in depository blockchains mutual access and cross-blockchain identity authentication. Trusted access across heterogeneous chains is gradually becoming a hot challenge. In order to ensure cross-blockchain trusted access, the majority of the current works focus on on-chain notaries and the relay chain model. However, these methods have the following drawbacks: 1) notaries on the chain are more vulnerable to attacks due to their high degree of centralization, which causes off-chain users to lose their trust and thus exacerbates the off-chain trust crisis; 2) although the relay model involves multiple parties in maintenance and supervision and enjoys a more robust trust, the paticipatant nodes are relatively fixed, which impose a terrible dilemma that invalid nodes cannot participate in consensus formation in a timely manner, thus progressively disrupting the connectivity of the relay across heterogeneous chains and eventually reducing the rate of trusted mutual access. In this article, we propose a novel general framework for cross-heterogeneous blockchain communication based on a periodical committee rotation mechanism to support information exchange of diverse transactions across multiple heterogeneous blockchain systems. Connecting heterogeneous blockchains through committees has a more robust trust than the notary method. In order to eliminate the impact of downtime nodes in a timely manner, we periodically reorganize the committee and give priority to replacing downed nodes to ensure the reliability of the system. In addition, a message-oriented verification mechanism is designed to improve the rate of trusted intervisit across heterogeneous chains. We have built a prototype of the scheme and conducted simulation experiments on the current mainstream blockchain for message exchange across heterogeneous chains. The results show that our solution has a good performance both in inter-chain access rate and system stability.

In this paper, a Generative Adversarial Network(GAN) is proposed for data augmentation of remote sensing images abstracted from Jiangsu province in China, i.e., D-sGAN(Deeply-supervised GAN). At First, to modulate the layer activations, a down-sampling scheme is designed based on the segmentation map. Then, the architecture of the generator is UNet++ with the proposed down-sampling module. Next, the generator of this net is deeply supervised by the discriminator using deep Convolutional Neural Network(CNN). This paper further proved that the proposed down-sampling module and the dense connection characteristics of UNet++ are significantly beneficial to the retention of semantic information of remote sensing images. Numerical results demonstrated that the images generated by D-sGAN could be used to improve accuracy of the segmentation network, with a better Fully Convolutional Networks Score(FCN-Score) compared to the GoGAN, SimGAN and CycleGAN models.

As a decentralized trusted database, the blockchain is finding applications in a growing number of fields such as finance, supply chain and medicine traceability, where large volumes of valuable data are stored on the blockchain. Currently, the mainstream blockchains employ a hybrid data storage architecture combining on-chain and off-chain storage. Real-time distributed search of mass data stored in this hybrid system is now a major need. However, previous fast retrieval schemes for the blockchain system are aimed only at on-chain data without considering their relevance to off-chain data, and thus fail to meet the requirement. In this paper, we propose an efficient blockchain data query scheme by introducing a novel Merkle Semantic Trie-based indexing technique without modifying the underlying database. A consensus on-chain index structure is constructed using the extracted semantic information of the off-chain data to create a mapping between the on-chain and off-chain data, thus enabling real-time data query both on and off the chain. Our scheme also provides multiple complex analytical query primitives to support semantic query, range query, and even fuzzy query. Experiments on three open data sets show that the proposed scheme has good query performance with shorter query latency for four different search types and offers better retrieval performance and verification efficiency than those available.

With the increasing demand for high speed and low latency services on the Internet of Vehicles, researches on wireless networks in intelligent connected vehicles (ICVs) with communication and caching capability have attracted much attention. Content retrieving in ICVs is subject to performance degradation as a result of channel fading and intermittent network connectivity. The emerging fifth-generation (5G) networks are promising in supporting the needs of data transmission and alleviating the communication problems in ICVs. Specifically, to improve the users' quality of experience (QoE) and reduce the access delay of content retrieval, it helps to leverage in-network caching in on-board units and small cell base stations (SBSs). In this paper, we propose a cooperative caching scheme based on content popularity and transmission power restriction for inhomogeneous ICV, which pre-caches content files at SBSs to significantly reduce content retrieval delay. In specific, we model the proposed system as a cache management problem and attain optimal QoE by allocating proper transmission power for each content file. Using extensive simulations, we demonstrate that the proposed solution can effectively provide service for ICVs with high QoE in different scenarios.

Mobile-edge computing (MEC) is a promising paradigm to improve the quality of computation experience of mobile devices because it allows mobile devices to offload computing tasks to MEC servers, benefiting from the powerful computing resources of MEC servers. However, the existing computation-offloading works have also some open issues: 1) security and privacy issues; 2) cooperative computation offloading; and 3) dynamic optimization. To address the security and privacy issues, we employ the blockchain technology that ensures the reliability and irreversibility of data in MEC systems. Meanwhile, we jointly design and optimize the performance of blockchain and MEC. In this article, we develop a cooperative computation offloading and resource allocation framework for blockchain-enabled MEC systems. In the framework, we design a multiobjective function to maximize the computation rate of MEC systems and the transaction throughput of blockchain systems by jointly optimizing offloading decision, power allocation, block size, and block interval. Due to the dynamic characteristics of the wireless fading channel and the processing queues at MEC servers, the joint optimization is formulated as a Markov decision process (MDP). To tackle the dynamics and complexity of the blockchain-enabled MEC system, we develop an asynchronous advantage actor–critic-based cooperation computation offloading and resource allocation algorithm to solve the MDP problem. In the algorithm, deep neural networks are optimized by utilizing asynchronous gradient descent and eliminating the correlation of data. The simulation results show that the proposed algorithm converges fast and achieves significant performance improvements over existing schemes in terms of total reward.

The fifth-generation (5G) mobile communication systems support the millimeter-wave (mmWave) communications, which enable content dissemination for enhanced V2X (eV2X) services. However, the current content dissemination architectures face various problems, such as limited radio coverage of mmWave communications and differentiated Quality-of-Experience (QoE) requirements of users. To address these, we propose a regional-centralized content dissemination (RC-CD) scheme for eV2X services. The RC-CD can deal with the requests from distributed vehicles by the regional-centralized service architecture. By introducing vehicle-to-vehicle and vehicle-to-infrastructure mmWave communications, the content dissemination services are expanded to the areas that the mmWave base stations cannot cover. According to different QoE requirements, the requests of eV2X services are categorized into two groups: 1) elastic requests and 2) inelastic requests. Our algorithm considers the channel characteristics of mmWave and the different QoE requirements of requests to jointly optimize the waiting time of elastic requests and the failure ratio of inelastic requests. It also adopts an efficient heuristic approximate algorithm to solve the NP-completed optimization problem. The performance of our proposed scheme is evaluated by simulations in a realistic city layout. The results show that our scheme can provide an efficient architecture for eV2X content dissemination that supports different types of requests, provides a better QoE for the users, and achieves broader service coverage.

To provide intelligent and personalized services on smart devices, machine learning techniques have been widely used to learn from data, identify patterns, and make automated decisions. Machine learning processes typically require a large amount of representative data that are often collected through crowdsourcing from end users. However, user data could be sensitive in nature, and training machine learning models on these data may expose sensitive information of users, violating their privacy. Moreover, to meet the increasing demand of personalized services, these learned models should capture their individual characteristics. This article proposes a privacy-preserving approach for learning effective personalized models on distributed user data while guaranteeing the differential privacy of user data. Practical issues in a distributed learning system such as user heterogeneity are considered in the proposed approach. In addition, the convergence property and privacy guarantee of the proposed approach are rigorously analyzed. The experimental results on realistic mobile sensing data demonstrate that the proposed approach is robust to user heterogeneity and offers a good tradeoff between accuracy and privacy.

Compared with individual recommendation, recommending services to a group of users is more complicated because of various users' preference should be considered and introduces new challenging such as fairness, which has never been well studied in current works. In this paper, we propose a novel recommendation scheme called PFGR, which combines a probabilistic model with coalition game strategy, to ensure the accuracy and fairness between groups of users. Given a group of users and a set of services, PFGR models a generative process for service selection in light of several observations: 1) each group is related with several topics; 2) users' decisions on the service selection depends on their expertise, the opinions of members they are familiar with, and group influence; 3) each group contains active users and inactive user, whose activeness contributes to the existence of group. PFGR first estimates the preference of each user on a candidate service via combining user's expertise, inherent connection, and group influence. Then, it determines a group's decision on a service by aggregating the preference of group members using adaptive weights. Finally, PFGR considers users' activeness and employs a strategy based on coalition game to produce a ranked list which is fair to each group member as much as possible. Experimental results on three real-world datasets validate that PFGR can achieve higher Hit Rate and Average Reciprocal Hit Rank than state-of-the-art approaches, which indicates that PFGR attains both the precision and fairness of recommendation.

As the prerequisite for the attacker to invade the target network, Persistent Scan and Foothold Attack (PSFA) is becoming progressively more subtle and complex. Even worse, the static and predictable characteristics of traditional systems provide an asymmetric advantage for attackers in launching the PSFA. To reverse this asymmetric advantage and resist the PSFA, two new defense ideas, called moving target defense (MTD) and deception-based cyber defense (DCD), have been suggested to provide the proactive selectable measures to complement traditional defense. However, MTD is unable to defeat the sophisticated attacker with fingerprint tracking ability. Meanwhile, DCD is easy to be marked by the attacker, which will result in a great waste of defense resources and poor defense effectiveness. To address this shortcoming, we propose the hybrid cyber defense mechanism that combines the address mutation (belonging to MTD) and fingerprint camouflage (belonging to DCD) strategies. More specifically, we first introduce and formalize the attacker model of PSFA based on the cyber kill chain. Afterwards, the traffic direction technology is designed to realize the coordination between the strategy of address mutation and the strategy of fingerprint camouflage. Furthermore, we construct the fine-grained quantitative modeling of the attacker’s behaviors through an in-depth observation of actual network confrontation. Based on this, a dynamic defense strategy generation algorithm is presented to maximize the effectiveness of our hybrid mechanism. Finally, the experimental results show that our hybrid mechanism can greatly improve the time required for a successful attack and achieve a better defense effect than the single strategy.

Robustness is the most important factor that limits the practical application of reversible watermarking. To deal with this issue, several robust reversible watermarking (RRW) techniques have been proposed. Among them, the two-stage RRW framework proposed by Coltuc et al. is a promising one. In the first state of this framework, a robust watermark is embedded into the cover image to provide robustness, and then in the second stage, the information enabling revert the robust embedding is reversibly embedded into the already marked image to guarantee the reversibility. However, because of using the same area for these two embedding stages, the robustness in the first stage is seriously weakened by the reversible embedding. As a result, this elegant method is not effective as expected. Based on this consideration, this paper proposes an independent embedding domain (ED)-based two-stage RRW. The cover image is first transformed into two independent EDs, and then the robust and reversible watermarks are embedded into each domain separately. The carrier derived from the first embedding stage that carrying the robust watermark will not change after the reversible embedding, and thus, the robustness of the first stage is well preserved. By the proposed method, the embedding performance of the original two-stage RRW is significantly enhanced. Moreover, the proposed method is experimentally verified better than some other state-of-the-art RRW methods.

Data centers are key participants in emergency demand response (EDR), where the grid coordinates large electricity consumers for reducing their consumption during emergency situations to prevent major economic losses. While existing literature concentrates on owner-operated data centers (e.g., Google), this work studies EDR in multi-tenant colocation data centers (e.g., Equinix) where servers are owned and managed by individual tenants and which are better targets of EDR. Existing EDR mechanisms incentivize tenants energy reduction. Such designs can either be gamed by strategic tenants or untrustworthy colocation operators for illegal gains. These serious privacy concerns stand as barrier preventing the tenants' participation in EDR. This paper addresses such concerns by proposing a privacy-preserving and strategy-proof mechanism using the descending clock auction. Privacy is protected by implementing homomorphic encryption for aggregation through the clock auction, where operator can only know the aggregate of the tenants' values or bids but not their individual private values or confidential information submitted to meet the EDR. We evaluate the privacy and performance of this scheme by formulating descending clock auction, in which the amount of energy/price the tenants are willing to reduce for a given price/energy to meet EDR is protected.

Vehicular named data networking (VNDN) has recently emerged as a novel paradigm to facilitate content-centric data sharing for Internet of Vehicles. However, an information holder can spread fake data to clients for malicious purposes, which may affect the driving decision of the recipient, or even worse, cause traffic congestion and accidents. In this article, we build a data-sharing system that consists of a double-layer blockchain. The nodes at the bottom layer request for service by announcing their requirements in the NDN paradigm. For the upper layer, the nodes submit their demands and supplies to the nearest roadside unit for further matching. We model the balance between the demand and supply as a matching game. To encourage nodes to provide positive services, a reputation management mechanism that combines negative and positive transaction records is proposed. Simulation results verify the validity of our system, and the data-sharing mechanism fosters a secure information interaction in the VNDN.

To improve the urban traffic condition and reduce accidents, we propose a platoon-driving model for autonomous vehicles in a free-flow traffic state in this article. This model allows vehicles with successful path matching to be grouped in a platoon and led by the platoon head (PH). In addition, a PH selection scheme is introduced to provide an incentive for vehicles to be PHs and maintain the dynamic update of platoons. Next, a smart contract is employed to enable the payment based on a blockchain between the PH and platoon members (PMs), avoiding the malicious and false payments. The numerical results show that the platoon model is superior to the individual driving model in terms of fuel consumption. The comparison between carpooling and noncarpooling modes within the platoon shows that our model has a better performance in terms of PH revenue and PM's service charge.

The application of blockchain to mobile edge computing (MEC) systems has attracted great interests. However, the design and optimization of blockchain and MEC in most existing works are done separately, which will result in sub-optimal performance. In this paper, we propose a joint optimization framework for blockchain-enabled MEC systems to achieve the optimal trade-off between the performance of the MEC system and the performance of the blockchain system. Specifically, both MEC and blockchain are considered as services in the framework, where energy consumption and delay/time to finality (DTF) are the performance metrics for the MEC system and the blockchain system, respectively. We formulate an optimization problem to achieve the optimal trade-off through jointly optimizing user association, data rate allocation, block producer scheduling, and computational resource allocation. To solve the problem, we decouple the optimization variables for efficient algorithm design. In addition, we develop an iterative algorithm for user association and data rate allocation and a bisection algorithm for computing resource allocation. Simulation results show the convergence of the proposed algorithms, and the proposed scheme can achieve the optimal trade-off between energy consumption and DTF.

Before the final attack happens, clandestine attackers conduct sequenced stages for being stealthy and elusive. These attacks can leave clues in several different log files. Howeverexisting approaches can only detect the anomalies using single type of log and fail to reveal all of the attack steps through log integration and correlation. Such methods can hardly detect the relationships among events and prevent the attack in advance. Additionally, traditional machine learning or data mining in log analysis has a high overhead in computing which is impractically applied in a real product or system. To address these problems, we present AClog, a multiple log correlated analysis system to construct the attack chain. Inspired by penetration testing and social network analysis, we transfer the attack provenance as an event relationship discover problem. We use different logs to form the steps of the system and regard them as the event sequences before the attack. Then, we leverage Fast Linear SVM and Longest Common Subsequences to find out the regular steps before the attack. Finally, we spot the corresponding log sequences to identify the pre- attackk steps proactively. We apply our approach in the attack prediction of a cloud computing platform and a university network. The results show that the proposed method can effectively and precisely construct the attack steps and identify the corresponding syslogs.

In Vehicular Ad Hoc Networks (VANETs), the unreliable wireless environment and highly dynamic topology make multi-content distribution inefficient due to the large amount of content requests from vehicles. This gives rise to the need for new content distribution schemes in VANETs. Current researches on content distribution for VANETs generally focus on the single type of content. In this paper, we consider both elastic (with no hard delay requirement) and inelastic (with a hard deadline) contents and propose a joint content distribution scheme in VANETs. We model the content distribution as an optimization problem which jointly minimizes the waiting delay of elastic requests and the failure ratio of inelastic requests. Then, we propose an efficient clonal selection-based approximate algorithm to solve the optimization problem. The performance of our scheme is evaluated by simulation using realistic vehicular traces. Simulation results show that our proposed scheme has better performance than previous solutions.

Unmanned Aerial Vehicles (UAV) have rapidly developed and been widely applied to military and civilian applications in recent years. Anomaly Detections and finding out the root causes are critically important for UAV social network security. In the UAV social networks, the drone can communicate with one another directly in a form of leading flights with followers during a far away mission. The ground controller cannot get their information directly. Besides, none of the works consider the privacy protection and anomaly root cause tracing during the distributed detection. This paper presents a self-verification approach among UAV flights which can check whether the flights have honestly obeyed the orders or suffered the anomalies. Besides, we do the verification without looking through the plaintext records or data of the drones. Finally, to instruct the drones to solve the problems, we trace the fundamental root causes leading to the anomalies by learning the fault tree. We apply our approach on raw UAV social network data and align our experiment with two former works as baselines for comparison. Our approach can reduce the time cost of verification from exponential growth to linear growth and improve the tracing accuracy rate around 4.3% higher than the former work.

Mobile crowdsensing (MCS) has gained popularity for its potential to leverage individual mobile devices to sense, collect, and analyze data instead of deploying sensors. As the sensing data become increasingly fine-grained and complicated, there is a tendency to enhance MCS with the edge computing paradigm to reduce time delays and high bandwidth costs. The sensing data may reveal personal information, and thus it is of great significance to preserve the privacy of the participants. However, preserving privacy may hinder the process of handling malicious participants. In this paper, we propose two privacy preserving reputation management schemes for edge computing enhanced MCS to simultaneously preserve privacy and deal with malicious participants. In the basic scheme, a novel reputation value updating method is designed based on the deviations of the encrypted sensing data from the final aggregating result. The basic scheme is efficient at the expense of revealing the deviation value of each participant to the reputation manager. To conquer this drawback, we propose an advanced scheme by updating the reputation values utilizing the rank of deviations. Extensive experiments demonstrate that both these two schemes have high cost efficiency and are effective to deal with malicious participants.

Exploiting relays in millimeter wave (mmWave) systems is an effective way to extend the communication coverage and overcome the blockage problem. This paper comprehensively studies secure transmissions in mmWave decode-and-forward (DF) relay systems. Depending on the overlapped resolvable paths between the main channel and the wiretap channel in each transmission stage, we consider three eavesdropping scenarios, namely two-stage eavesdropping (TSE), single-stage eavesdropping (SSE) and no eavesdropping (NE). We investigate secrecy performance and optimal parameter design of these eavesdropping scenarios under the same codeword transmission (SCT) scheme and the different codewords transmission (DCT) scheme, where source and relay utilize same codeword or different codewords. Specifically, we derive closed-form expressions for connection probability and secrecy outage probability, and then give solution to the secrecy throughput maximization problem. Furthermore, we investigate the effectiveness of the artificial noise (AN) by evaluating the secrecy performance of AN assisted transmissions. Numerical results are provided to verify our theoretical analysis. Our results give insights into the secure transmission scheme selection and the impact of various parameters, such as number of antennas, power allocation between source and relay, number of overlapped paths, and distances between different nodes, on the secrecy performance of the mmWave relay system.

Information-centric networking (ICN) is developed for the future Internet because of the tremendous increase of content demands in the Internet. In the ICN architecture, in-network storage for caching plays an important role in improving content delivery efficiency, scalability and availability. To enjoy the benefits of caching users' preferable contents without disclosing the users' privacy, in this paper, we aim to integrate local differential privacy (LDP) techniques into data-driven optimization, and propose a novel scheme to allow content provider (CP) to collect the locally differentially private content preferences of a selected group of users, exploit data-driven approach to predict the content popularity, and offer the cache-enabled access points (APs) economic incentives to cache the selected preferable content. Here, optimized local hashing (OLH) is employed to locally add differential private noise to the users' preference content information and the noisy data is sent to the CP. Besides, we leverage data-driven methodology to predict the content popularity according to the constructed reference distribution of the given noisy preference content data from users. We formulate a data-driven caching revenue optimization, provide feasible solutions, and conduct simulations to show the effectiveness of the proposed scheme.

Recommender systems have been recognized as an effective way to deal with the information overload problem, which can recommend accurate and positive items to users from a large volume of choices. Due to its capability and simplicity, collaborative filtering (CF) is one of the most popular techniques for recommender systems. However, CF suffers from three issues which are user cold-start, item cold-start and data sparsity problems. These issues severely degrade the performance of CF. To address these issues, a hybrid collaborative filtering recommendation model, termed TrustCF, is proposed in this paper, based on user-item ratings and trust relations among users. TrustCF integrates ratings from trusted friends and similar users, ratings of similar items, item reputation and user history ratings. In particular, we modify the similarity calculation formula, considering the effect of the number of co-ratings. Trust relations among users are used to make predictions. In this way, TrustCF can alleviate the data sparsity problem and improve the recommendation performance. Experimental results on two real-world datasets verify the effectiveness of the proposed TrustCF model and show TrustCF has better recommendation accuracy than other five counterparts.

We propose a novel wireless technique named pinpoint waveforming to achieve the location-restricted service access control, i.e., providing wireless services to users at eligible locations only. The proposed system is inspired by the fact that when two identical wireless signals arrive at a receiver simultaneously, they will constructively interfere with each other to form a boosted signal whose amplitude is twice of that of an individual signal. As such, the location-restricted service access control can be achieved through transmitting at a weak power, so that receivers at undesired locations (where the constructive interference vanishes), will experience a low signal-to-noise ratio (SNR), and hence a high bit error rate that retards the correct decoding of received messages. At the desired location (where the constructive interference happens), the receiver obtains a boosted SNR that enables the correct message decoding. To solve the difficulty of determining an appropriate transmit power, we propose to entangle the original transmit signals with jamming signals of opposite phase. The jamming signals can significantly reduce the SNR at the undesired receivers but cancel each other at the desired receiver to cause no impact. With the jamming entanglement, the transmit power can be any value specified by the system administrator. To enable the jamming entanglement, we create the channel calibration technique that allows the synchronization of transmit signals at the desired location. We develop a prototype system using the Universal Software Defined Radio Peripherals (USRPs). The evaluation results show that the receiver at the desired location obtains a throughput ranging between 0.9 and 0.93, whereas an eavesdropper that is 0.3 meter away from a desired location has a throughput approximately equal to 0.

Recently, people have witnessed a remarkable growth in the number of smart wearable devices. Accompanied with the development of a contactless data transmission technique, the lack of effective secret key establishment between lightweight wearable devices which support contactless data transmission technique becomes a security bottleneck. In this paper, we propose a novel wireless key establishment method by moving or shaking the wearable wireless devices. Instead of received signal strength (RSS) itself, we denote the RSS trajectories of two moving wireless devices as the materials of secret key. Moreover, inspired by channel reciprocity in a channel feature-based key establishment technique, we propose the concept of reciprocity of RSS trajectory that guarantees that even when the RSSs of two devices are the same, the identical RSS trajectories of two devices can successfully generate the secret key. In addition, to effectively utilize the RSS trajectories, we design a novel quantization scheme by considering the entropy and efficiency of key generation. Furthermore, we analyze the security of this key establishment procedure in an eavesdropped and monitored environment. We also perform an evaluation of 64-, 128-, 192-, and 256-b key generation in indoor/outdoor environment, and the results indicate that the times are 0.22/0.33, 0.61/0.74, 0.95/1.02, and 1.28/1.46 s, respectively. In addition, the ranges of efficiency and entropy are 0.654-0.795 and 0.968-0.993.

In the above paper, the following acknowledgment of financial support was not included, due to a publication error.

In this paper, we investigate the problem of integrity auditing for cloud deduplication storage. Specifically, in addition to the outsourced data confidentiality, we also aim to ensure the integrity of the deduplicated cloud storage. With the existing works based on Provable Data Possession (PDP)/Proof of Retrievability (PoR), we are either required to rely on a fully trusted proxy server or inevitably sacrifice the privacy and efficiency. In contrast, we present a novel message-locked integrity auditing scheme without an additional proxy server, which is applicable to both file-level and chunk-level deduplication systems. In particular, our scheme is storage efficient in the sense that apart from eliminating the ciphertext redundancy, we also enable the integrity tag deduplication by a message-derived signing key, which merely incurs minimal client-side computation overhead. Besides, we can still publicly perform the integrity check over any client's cloud storage by incorporating the proxy re-signature technique. We show that the proposed scheme will not disclose the data ownership information and is provably secure under the Computational Diffie-Hellman (CDH) assumption in the random oracle model. Finally, the performance evaluation demonstrates its effectiveness and efficiency.

Privacy protection has recently attracted increasingly attention in location-based services (LBS) with the development of wireless communication and mobile positioning technology. Many location-based cloaking algorithms are proposed to protect location privacy of mobile users. However, there is a scenario where the anonymous server only utilizes users defined as current users in our algorithm, who are requiring LBS requests at the current time, to form the cloaking region. If there are not enough current users at the current time, the generated cloaking region will be larger than expected. To solve this problem, we propose the probability-base location prediction ( PLP ) algorithm. Mobile users are divided into current users and historical users. According to predicting probability, historical users are also utilized to generate the cloaking region when current users are not enough to achieve the k-anonymity model. Experimental results show that PLP can predict the cloaking region as high as 90% and the cloaking region can also decrease remarkably.

Authentication is the first step to access a resource (service, website, data, etc.), so it is of vital importance in a system. The most widely used authentication mechanisms are one-factor authentication based on password and two-factor authentication methods which require a password and another factor (verification code, biometric feature, hardware token, software plug-in, etc.). However, in many public areas, passwords may be exposed to other monitoring equipments or even other people; while authentication for the second factor always requires human-machine interaction. As a result, password might suffer misuse by others; the latter may need extra procedures and incur long delay, decreasing usability and deployability of the system. In this paper, we propose QuickAuth, which aims to develop a simple, yet quick authentication method that does not rely on password such that the entire authentication procedure can be implemented automatically with minimal user involvement. In QuickAuth, one authentication factor is the user's cellphone, and the other is the proximity of the cellphone to the computer which the user wants to login to. The proximity of the two devices is obtained by comparing ambient sound recorded by microphones. Through the real-world implementation and evaluation, we show that QuickAuth works well in terms of usability, deployability, and security in the environment of public areas.

We propose a novel wireless technique named pinpoint waveforming to achieve the location-restricted service access control, i.e., providing wireless services to users at eligible locations only. The proposed system is inspired by the fact that when two identical wireless signals arrive at a receiver simultaneously, they will constructively interfere with each other to form a boosted signal whose amplitude is twice of that of an individual signal. As such, the location-restricted service access control can be achieved through transmitting at a weak power, so that receivers at undesired locations (where the constructive interference vanishes), will experience a low signal-to-noise ratio (SNR), and hence a high bit error rate that retards the correct decoding of received messages. At the desired location (where the constructive interference happens), the receiver obtains a boosted SNR that enables the correct message decoding. To solve the difficulty of determining an appropriate transmit power, we propose to entangle the original transmit signals with jamming signals of opposite phase. The jamming signals can significantly reduce the SNR at the undesired receivers but cancel each other at the desired receiver to cause no impact. With the jamming entanglement, the transmit power can be any value specified by the system administrator. To enable the jamming entanglement, we create the channel calibration technique that allows the synchronization of transmit signals at the desired location. We develop a prototype system using the Universal Software Defined Radio Peripherals (USRPs). The evaluation results show that the receiver at the desired location obtains a throughput ranging between 0.9 and 0.93, whereas an eavesdropper that is 0.3 meter away from a desired location has a throughput approximately equal to 0.

Cognitive Radio (CR) technique is proved to be an efficient approach for mitigating the spectrum scarcity problem in wireless communications and spectrum allocation methods construct the foundation of such a technique. However, it will degrade the performance of CR when paying no attention to the behavior of second users (SUs) and their demands for spectrum attribute. In this paper, the spectrum allocation problem is first modeled as a coalition formation game, taking SUs reputation and requirements of spectrums into consideration. The rule named Assigning spectrum by probability among coalitions and by demand within coalitions is used to optimize the spectrum utilization and fairness when allocating spectrum among SUs. For each SU is equipped with an agent, a central authority is not needed and therefore the scheme can be more applicable in dynamic cognitive radio networks. Simulation results show that the proposed approach can efficiently improve the fairness and efficiency of spectrum allocation in CR context.

The multimedia social network (MSN), a combination of the multimedia sharing technology and social network, has prominent social features and diffusion characteristics. Owing to its centerlessness and lack of regulation, MSNs have some serious network environment problems, such as spread of negative digital content and serious data redundancy. To solve the above problems, this paper proposes a strong and weak ties feedback-based trust model in MSNs on the basis of the Weak Ties Theory of sociology. This model evaluates the trust level from two different aspects, multimedia content and user behaviors, and computes the reputation value by the Bayesian estimation principle and the damped window mechanism. On the basis of the trust model, we establish a trust-based information dissemination model in MSNs to study the relationship between trust and digital content dissemination. Simulation results indicate that the trust model is reliable in design, valid in network transmission, and effective in resisting malicious feedback and collusive attacks, enables positive digital data to spread rapidly and widely, and limits the dissemination of negative content.

As one of the most efficient multi-secret visual cryptography (MVC) schemes, the tagged visual cryptography (TVC) is capable of hiding tag images into randomly selected shares. However, the encoding processes of TVC and other MVC schemes bring distortion to shares, which definitely lowers the visual quality of the decoded secret image. This letter proposes an extended TVC scheme, named as lossless TVC (LTVC). Specifically, “lossless” means that the proposed LTVC scheme encodes the tag image without affecting the rebuilt secret image, i.e., the decoded secret image of LTVC has the same visual quality with that of the conventional VC scheme . Moreover, we propose the probabilistic LTVC (P-LTVC) to solve the potential security problem of LTVC. Finally, the superiority of the proposed scheme is experimentally verified.

As low-cost tags based on the EPC C-1 G-2 standard are much limited in storage capacity and computation power, most of the existing authentication protocols are too complicated to be suitable for these tags, and the design of authentication protocols conforming to the EPC C-1 G-2 standard is a big challenge. Recently, a mutual authentication protocol for RFID conforming to the EPC C-1 G-2 standard was proposed by Yeh et al., and it is claimed that this protocol has solved all security vulnerabilities in the existing RFID protocols. However, in fact, it is proven that this scheme is vulnerable to the tag tracing attack and suffers from the information leakage issue, and the complexity of the successful attack is only 216. To address these issues efficiently, a novel secure RFID authentication protocol conforming to the EPC C-1 G-2 standard is proposed. In the new scheme, the attack complexity is raised to 232 without changing the length of any protocol data. Analysis shows that our protocol can not only efficiently resist the tag information leakage and the tag tracing attack, but also have a significant advantage in performance over Yeh et al.'s protocol.

In recent years, Cognitive Radio (CR) has been regarded as the most promising technique for solving the problem of spectrum utilization. CR can scan the spectrum band and identify free channels which will be used by cognitive users with no harm to primary users. Due to the various dynamic characteristics of Cognitive Radio Networks (CRN), adaptation and secure communication are of greater significance than other wireless networks. In this paper, we propose an adaptive trust management mechanism based on cognition cycle, which can mitigate system error rate effectively and make spectrum allocation more reasonable and secure. Finally, simulation results show that the scheme has the advantages of strong adaptation and low error rate.

Multicasting is an important business in the field of the wireless local area network (WLAN), because the access point (AP) usually has to send the same message to each station (STA) of a specific group, and broadcasting the message to this group is one of the most efficient ways of communication. Chinese WLAN security standard, called WLAN Authentication and Privacy Infrastructure (WAPI), has taken secure multicasting into account, and proposed a Multicast Key Management Protocol (MKMP), in which the multicast session key (MSK) is distributed to each STA over the secure unicast channel built between STA and AP one by one. It is clear that the MSK distribution is very inefficient in performance, especially when the number of STAs is very large. In this study, a new MSK distribution protocol is proposed, and it can be used to substitute the original protocol in WAPI. Analyses show that the proposed protocol can achieve needed security requirements, and is more efficient than the original one in WAPI. Now, WAPI has been in the process of ISO/IEC standard building, and thus the authors think that their proposal can ameliorate WAPI largely and promote its ISO/IEC standard building.

Sensor networks are composed of a large number of low power sensor devices. For secure communication among sensors, secret keys are required to be established between them. Considering the strict resource constraints of sensors, key infection has been proposed by Anderson, Chan, and Perrig. However, because the communication keys are broadcasted in plaintext in key infection, some of them may be eavesdropped by an adversary. To address this security issue, secrecy transfer is presented, which utilizes pre-loaded secret keying material to enhance the security performance of key infection. To thwart on-going cryptanalytic attacks, a key evolution scheme is proposed to continuously refresh shared keys. Key evolution forces the adversary to keep monitoring traffic all the time after compromising a key; even if the adversary has compromised a key, it cannot catch up with the key evolution process, and may lose control of the compromised key quickly in a noisy communication environment. Analysis results show that key infection, secrecy transfer, and key evolution present viable trade-offs between security and resource consumption for smart dust sensor networks.

Based on the analysis to the phenomenon and methods of denial-of-sleep attacking in wireless sensor network, a scheme is proposed employing fake schedule switch with RSSI measurement aid. The sensor nodes can reduce and weaken the harm from collision, exhaustion and broadcast attack and on the contrary make the attackers lose their energy quickly so as to die. Simulation results show that at a bit price of energy and delay, network health can be guaranteed and packets drop ratio has been decreased compare with original scenario without our scheme.

Trust management is an important issue in wireless sensor networks (WSNs). In this paper, we introduce the concept of trust and design a distributed event- triggered trust management model for WSNs. It combines cryptography, statistics, economics, data analysis and the other related fields. In this way, we can immediately identify and isolate the malice node, thereby creating a secure and reliable wireless sensor networks that can avoid some common attacks and ensure the security of the applications. And, we give the communication process and the computation model as well as how each trust management module works. So it is no longer a simple calculation model or a simple frame structure, and it has realistic feasibility and operability.

Wireless sensor networks are open architectures, so any potential threat can easily intercept, wiretap and counterfeit the information. Therefore, the safety of WSN is very important. Since any single key system cannot guarantee the security of the wireless sensor network for communications, this paper introduces a hierarchical key management scheme based on the different abilities of different sensor nodes in the clustered wireless sensor network. In this scheme, the nodes are distributed into several clusters, and a cluster head must be elected for each cluster. Private communication between cluster heads is realized through the encryption system based on the identity of each head while private communication between cluster nodes in a same cluster head is achieved through the random key preliminary distribution system. For cluster head node plays a pivotal role in this scheme, a trust management system should be introduced into the election of the cluster head which will exclude the malicious node from outside the cluster, thus improve the whole network security.

We present an attack to current interface copy protection systems and a new framework to restrict contents flowing within legal devices. The attack is named as interface replacement attack, which is motivated by the fact that a damaged interface usually can be replaced with a small cost. The new framework deploys security mechanisms in both interior part of a consumer electronic device and interfaces on it. We name it as deep copy protection framework to distinguish the current interface-centric copy protection frameworks. We believe that this viewpoint is novel and can be further studied to develop new copy protection system.

Insider attacks is a well-known problem acknowledged as a threat as early as 1980s. The threat is attributed to legitimate users who take advantage of familiarity with the computational environment and abuse their privileges, can easily cause significant damage or losses. In this paper, we present an active defense model and framework of insider threat detection and sense. Firstly, we describe the hierarchical framework which deal with insider threat from several aspects, and subsequently, show a hierarchy-mapping based insider threats model, the kernel of the threats detection, sense and prediction. The experiments show that the model and framework could sense the insider threat in real-time effectively.

Digital Rights Management ecosystem is composed of various participants, which adopt different security policies to meet their own security requirements, with a goal to achieve individual optimal benefits. However, from the perspective of the whole DRM-enabling contents industry, a simple adoption of several increasingly enhanced security policies does not necessarily implement an optimal benefit balance among participants. A game-theoretic analysis of adoptions of security policies was emphasized based on a proposed General DRM value chain ecosystem without the loss of generality. First, we formalized security policies and fundamental properties that include internal relativity and external one, together with multiparty game on adoptions of security policies. Also, a cooperative game among digital Contents Provider, Rights/Service Provider and digital Devices Provider, as well as a non-cooperative game between Providers and Consumers were presented. Final, a stable core allocation of benefits and Nash Equilibriums were found out, respectively. It is clearly concluded that the cooperative game has important super-addivitity and convexity, thus simultaneous adoptions of security policies with external relativity being helpful to achieve Pareto Optimality by using a pre-established cooperative relation; and that Pareto Optimality also exists between Providers and Consumer with the increase of users' purchase transactions when both have a repeated game.

Based on the analysis of the node selfishness and the drawback of min-hop selection method as the unique routing selection criteria in ad hoc networks, a non-intrusive multi-metric ad hoc routing protocol-NIMR is presented. By computing and storing the node fame, NIMR greatly attenuates the influence of node selfishness; By crossing-design between MAC layer and network layer, we employ a non-intrusive real-time available bandwidth measurement scheme to solve the congestion problem. Finally, we propose a new metric as the routing selection criteria, which combines fame, available bandwidth and minimum hops by weight. Simulation results show, Compared with DSR, fairness between nodes is improved and congestion control and load balance is implemented using NIMR without additionally increasing the network load. At the same time average life-span and end-to-end throughput is increased, average end-to-end delay is decreased using NIMR.