Search

Mixture-of-Experts (MoE) is an emerging technique for scaling large models with sparse activation. MoE models are typically trained in a distributed manner with an expert parallelism scheme, where experts in each MoE layer are distributed across multiple GPUs. However, the default expert parallelism suffers from the heavy network burden due to the all-to-all intermediate data exchange among GPUs before and after the expert run. Some existing works have proposed to reduce intermediate data exchanges by transferring experts to reduce the network loads, however, which would decrease parallelism level of expert execution and make computation inefficient. The weaknesses of existing works motivate us to explore whether it is possible to reduce inter-GPU traffic while maintaining a high degree of expert parallelism. This paper gives a positive response by presenting Luffy, a communication-efficient distributed MoE training system with two new techniques. First, Luffy migrates sequences among GPUs to hide heavy token pulling paths within GPUs and avoid copying experts over GPUs. Second, we propose token condensation that identifies similar tokens and then eliminates redundant transmissions. We implement Luffy based on PyTorch and evaluate its performance on a testbed of 16 V100 GPUs. Luffy system can achieve a speedup of up to 2.73x compared to state-of-the-art MoE training systems.

In this paper, we investigate a secure communication architecture based on unmanned aerial vehicle (UAV), which enhances the security performance of the communication system through UAV trajectory optimization. We formulate a control problem of minimizing the UAV flight path and power consumption while maximizing secure communication rate over infinite horizon by jointly optimizing UAV trajectory, transmit beamforming vector, and artificial noise (AN) vector. Given the non-uniqueness of optimization objective and significant coupling of the optimization variables, the problem is a non-convex optimization problem which is difficult to solve directly. To address this complex issue, an alternating-iteration technique is employed to decouple the optimization variables. Specifically, the problem is divided into three subproblems, i.e., UAV trajectory, transmit beamforming vector, and AN vector, which are solved alternately. Additionally, considering the susceptibility of UAV trajectory to disturbances, the model predictive control (MPC) approach is applied to obtain UAV trajectory and enhance the system robustness. Numerical results demonstrate the superiority of the proposed optimization algorithm in maintaining accurate UAV trajectory and high secure communication rate compared with other benchmark schemes.

In this paper, we propose a full-duplex integrated sensing and communication (ISAC) system enabled by a movable antenna (MA). By leveraging the characteristic of MA that can increase the spatial diversity gain, the performance of the system can be enhanced. We formulate a problem of minimizing the total transmit power consumption via jointly optimizing the discrete position of MA elements, beamforming vectors, sensing signal covariance matrix and user transmit power. Given the significant coupling of optimization variables, the formulated problem presents a non-convex optimization challenge that poses difficulties for direct resolution. To address this challenging issue, the discrete binary particle swarm optimization (BPSO) algorithm framework is employed to solve the formulated problem. Specifically, the discrete positions of MA elements are first obtained by iteratively solving the fitness function. The difference-of-convex (DC) programming and successive convex approximation (SCA) are used to handle non-convex and rank-1 terms in the fitness function. Once the BPSO iteration is complete, the discrete positions of MA elements can be determined, and we can obtain the solutions for beamforming vectors, sensing signal covariance matrix and user transmit power. Numerical results demonstrate the superiority of the proposed system in reducing the total transmit power consumption compared with fixed antenna arrays.

As the implementation of machine learning (ML) systems becomes more widespread, especially with the introduction of larger ML models, we perceive a spring demand for massive data. However, it inevitably causes infringement and misuse problems with the data, such as using unauthorized online artworks or face images to train ML models. To address this problem, many efforts have been made to audit the copyright of the model training dataset. However, existing solutions vary in auditing assumptions and capabilities, making it difficult to compare their strengths and weaknesses. In addition, robustness evaluations usually consider only part of the ML pipeline and hardly reflect the performance of algorithms in real-world ML applications. Thus, it is essential to take a practical deployment perspective on the current dataset copyright auditing tools, examining their effectiveness and limitations. Concretely, we categorize dataset copyright auditing research into two prominent strands: intrusive methods and non-intrusive methods, depending on whether they require modifications to the original dataset. Then, we break down the intrusive methods into different watermark injection options and examine the non-intrusive methods using various fingerprints. To summarize our results, we offer detailed reference tables, highlight key points, and pinpoint unresolved issues in the current literature. By combining the pipeline in ML systems and analyzing previous studies, we highlight several future directions to make auditing tools more suitable for real-world copyright protection requirements., Comment: To appear in the IEEE Symposium on Security and Privacy 2025, San Francisco, CA, USA

Large Model (LM) agents, powered by large foundation models such as GPT-4 and DALL-E 2, represent a significant step towards achieving Artificial General Intelligence (AGI). LM agents exhibit key characteristics of autonomy, embodiment, and connectivity, allowing them to operate across physical, virtual, and mixed-reality environments while interacting seamlessly with humans, other agents, and their surroundings. This paper provides a comprehensive survey of the state-of-the-art in LM agents, focusing on the architecture, cooperation paradigms, security, privacy, and future prospects. Specifically, we first explore the foundational principles of LM agents, including general architecture, key components, enabling technologies, and modern applications. Then, we discuss practical collaboration paradigms from data, computation, and knowledge perspectives towards connected intelligence of LM agents. Furthermore, we systematically analyze the security vulnerabilities and privacy breaches associated with LM agents, particularly in multi-agent settings. We also explore their underlying mechanisms and review existing and potential countermeasures. Finally, we outline future research directions for building robust and secure LM agent ecosystems., Comment: 35 pages, 23 figures, 9 tables

Long-range (LoRa) communication technology, distinguished by its low power consumption and long communication range, is widely used in the Internet of Things. Nevertheless, the LoRa MAC layer adopts pure ALOHA for medium access control, which may suffer from severe packet collisions as the network scale expands, consequently reducing the system energy efficiency (EE). To address this issue, it is critical to carefully allocate transmission parameters such as the channel (CH), transmission power (TP) and spreading factor (SF) to each end device (ED). Owing to the low duty cycle and sporadic traffic of LoRa networks, evaluating the system EE under various parameter settings proves to be time-consuming. Consequently, we propose an analytical model aimed at calculating the system EE while fully considering the impact of multiple gateways, duty cycling, quasi-orthogonal SFs and capture effects. On this basis, we investigate a joint CH, SF and TP allocation problem, with the objective of optimizing the system EE for uplink transmissions. Due to the NP-hard complexity of the problem, the optimization problem is decomposed into two subproblems: CH assignment and SF/TP assignment. First, a matching-based algorithm is introduced to address the CH assignment subproblem. Then, an attention-based multiagent reinforcement learning technique is employed to address the SF/TP assignment subproblem for EDs allocated to the same CH, which reduces the number of learning agents to achieve fast convergence. The simulation outcomes indicate that the proposed approach converges quickly under various parameter settings and obtains significantly better system EE than baseline algorithms.

In mobile edge computing systems, base stations (BSs) equipped with edge servers can provide computing services to users to reduce their task execution time. However, there is always a conflict of interest between the BS and users. The BS prices the service programs based on user demand to maximize its own profit, while the users determine their offloading strategies based on the prices to minimize their costs. Moreover, service programs need to be pre-cached to meet immediate computing needs. Due to the limited caching capacity and variations in service program popularity, the BS must dynamically select which service programs to cache. Since service caching and pricing have different needs for adjustment time granularities, we propose a two-time scale framework to jointly optimize service caching, pricing and task offloading. For the large time scale, we propose a game-nested deep reinforcement learning algorithm to dynamically adjust service caching according to the estimated popularity information. For the small time scale, by modeling the interaction between the BS and users as a two-stage game, we prove the existence of the equilibrium under incomplete information and then derive the optimal pricing and offloading strategies. Extensive simulations based on a real-world dataset demonstrate the efficiency of the proposed approach.

Mobile crowdsensing (MCS) has emerged as a prominent trend across various domains. However, ensuring the quality of the sensing data submitted by mobile users (MUs) remains a complex and challenging problem. To address this challenge, an advanced method is required to detect low-quality sensing data and identify malicious MUs that may disrupt the normal operations of an MCS system. Therefore, this article proposes a prediction- and reputation-based truth discovery (PRBTD) framework, which can separate low-quality data from high-quality data in sensing tasks. First, we apply a correlation-focused spatial-temporal transformer network to predict the ground truth of the input sensing data. Then, we extract the sensing errors of the data as features based on the prediction results to calculate the implications among the data. Finally, we design a reputation-based truth discovery (TD) module for identifying low-quality data with their implications. Given sensing data submitted by MUs, PRBTD can eliminate the data with heavy noise and identify malicious MUs with high accuracy. Extensive experimental results demonstrate that PRBTD outperforms the existing methods in terms of identification accuracy and data quality enhancement.

Semantic communication, emerging as a breakthrough beyond the classical Shannon paradigm, aims to convey the essential meaning of source data rather than merely focusing on precise yet content-agnostic bit transmission. By interconnecting diverse intelligent agents (e.g., autonomous vehicles and VR devices) via semantic communications, the semantic communication networks (SemComNet) supports semantic-oriented transmission, efficient spectrum utilization, and flexible networking among collaborative agents. Consequently, SemComNet stands out for enabling ever-increasing intelligent applications, such as autonomous driving and Metaverse. However, being built on a variety of cutting-edge technologies including AI and knowledge graphs, SemComNet introduces diverse brand-new and unexpected threats, which pose obstacles to its widespread development. Besides, due to the intrinsic characteristics of SemComNet in terms of heterogeneous components, autonomous intelligence, and large-scale structure, a series of critical challenges emerge in securing SemComNet. In this paper, we provide a comprehensive and up-to-date survey of SemComNet from its fundamentals, security, and privacy aspects. Specifically, we first introduce a novel three-layer architecture of SemComNet for multi-agent interaction, which comprises the control layer, semantic transmission layer, and cognitive sensing layer. Then, we discuss its working modes and enabling technologies. Afterward, based on the layered architecture of SemComNet, we outline a taxonomy of security and privacy threats, while discussing state-of-the-art defense approaches. Finally, we present future research directions, clarifying the path toward building intelligent, robust, and green SemComNet. To our knowledge, this survey is the first to comprehensively cover the fundamentals of SemComNet, alongside a detailed analysis of its security and privacy issues.

This paper focuses on semi-supervised crowd counting, where only a small portion of the training data are labeled. We formulate the pixel-wise density value to regress as a probability distribution, instead of a single deterministic value. On this basis, we propose a semi-supervised crowd-counting model. Firstly, we design a pixel-wise distribution matching loss to measure the differences in the pixel-wise density distributions between the prediction and the ground truth; Secondly, we enhance the transformer decoder by using density tokens to specialize the forwards of decoders w.r.t. different density intervals; Thirdly, we design the interleaving consistency self-supervised learning mechanism to learn from unlabeled data efficiently. Extensive experiments on four datasets are performed to show that our method clearly outperforms the competitors by a large margin under various labeled ratio settings. Code will be released at https://github.com/LoraLinH/Semi-supervised-Counting-via-Pixel-by-pixel-Density-Distribution-Modelling., Comment: This is the technical report of a paper that was submitted to IEEE Transactions and is now under review

Natural or man-made disasters pose significant challenges for delivering critical relief to affected populations due to disruptions in critical infrastructures and logistics networks. Unmanned aerial vehicles (UAVs)-aided disaster relief networks (UDRNs) leverage UAVs to assist existing ground relief networks by swiftly assessing affected areas and timely delivering lifesaving supplies. To meet the growing demands for collaborative, trust-free, and transparent UDRN services, blockchain-based UDRNs emerge as a promising approach through immutable ledgers and distributed smart contracts. However, several efficiency and security challenges hinder the deployment of blockchain-based UDRNs, including the lack of cooperation between smart contracts, lack of dynamic audit for smart contract vulnerabilities, and low forensics robustness against transaction malleability attacks. Towards efficient and secure blockchain-based UDRNs, this paper presents potential solutions: (i) a series of collaborative smart contracts for coordinated relief management, (ii) a dynamic contract audit mechanism to prevent known/unknown contract vulnerabilities; and (iii) a robust transaction forensics strategy with on/off-chain cooperation to resist transaction malleability attacks. Our prototype implementation and experimental results demonstrate the feasibility and effectiveness of our approach. Lastly, we outline key open research issues crucial to advancing this emerging field., Comment: 7 pages, accepted by IEEE Communications Magazine in August 2024

The rise of advanced persistent threats (APTs) has marked a significant cybersecurity challenge, characterized by sophisticated orchestration, stealthy execution, extended persistence, and targeting valuable assets across diverse sectors. Provenance graph-based kernel-level auditing has emerged as a promising approach to enhance visibility and traceability within intricate network environments. However, it still faces challenges including reconstructing complex lateral attack chains, detecting dynamic evasion behaviors, and defending smart adversarial subgraphs. To bridge the research gap, this paper proposes an efficient and robust APT defense scheme leveraging provenance graphs, including a network-level distributed audit model for cost-effective lateral attack reconstruction, a trust-oriented APT evasion behavior detection strategy, and a hidden Markov model based adversarial subgraph defense approach. Through prototype implementation and extensive experiments, we validate the effectiveness of our system. Lastly, crucial open research directions are outlined in this emerging field., Comment: This work has been accepted by IEEE NETWORK in April 2024. 9 pages, 5 figures, 1 table

With the rapid development of communication technologies and extended reality (XR), the services and applications of the Metaverse are gradually entering our lives. However, the current development of the Metaverse provides users with services that are homogeneous with the user experience that the Internet has brought in the past, making them more like an extension of the Internet. In addition, as a mobile application carrier for the Metaverse, it is also worth considering how vehicles with diverse onboard components can develop in synergy with the Metaverse. In this article, we focus on the core of the Metaverse, namely user experience, and provide a road map from Metaverse to Metaverse vehicles (Metavehicles). Specifically, we first elaborate on six features of the Metaverse from the perspective of user experience and propose a hierarchical framework for the Metaverse based on the evolutionary logic of the features. Under the guidance of this framework, we discuss the empowerment of onboard components of Metavehicles on the development of the Metaverse, and analyze the service experience that Metavehicles can bring to two types of users, namely drivers and passengers. Finally, considering the differentiated development levels of Metaverse and autonomous driving, we further establish a hierarchical framework for Metavehicles from three aspects (i.e., enhance Metaverse, enhance driving experience, and enhance entertainment experience), providing an evolutionary path for the development of Metavehicles., Comment: 7 pages, 5 figures

Advanced persistent threat (APT) is a kind of stealthy, sophisticated, and long-term cyberattack that has brought severe financial losses and critical infrastructure damages. Existing works mainly focus on APT defense under stable network topologies, while the problem under time-varying dynamic networks (e.g., vehicular networks) remains unexplored, which motivates our work. Besides, the spatiotemporal dynamics in defense resources, complex attackers' lateral movement behaviors, and lack of timely defense make APT defense a challenging issue under time-varying networks. In this paper, we propose a novel game-theoretical APT defense approach to promote real-time and optimal defense strategy-making under both periodic time-varying and general time-varying environments. Specifically, we first model the interactions between attackers and defenders in an APT process as a dynamic APT repair game, and then formulate the APT damage minimization problem as the precise prevention and control (PPAC) problem. To derive the optimal defense strategy under both latency and defense resource constraints, we further devise an online optimal control-based mechanism integrated with two backtracking-forward algorithms to fastly derive the near-optimal solution of the PPAC problem in real time. Extensive experiments are carried out, and the results demonstrate that our proposed scheme can efficiently obtain optimal defense strategy in 54481 ms under seven attack-defense interactions with 9.64$\%$ resource occupancy in stimulated periodic time-varying and general time-varying networks. Besides, even under static networks, our proposed scheme still outperforms existing representative APT defense approaches in terms of service stability and defense resource utilization.

This paper investigates the utilization of simultaneously transmitting and reflecting RIS (STAR-RIS) in supporting joint physical layer security (PLS) and covert communications (CCs) in a multi-antenna millimeter wave (mmWave) system, where the base station (BS) communicates with both covert and security users while defeating eavesdropping by wardens with the help of a STAR-RIS. Specifically, analytical derivations are performed to obtain the closed-form expression of warden's minimum detection error probability (DEP). Furthermore, the asymptotic result of the minimum DEP and the lower bound of the secure rates are derived, considering the practical assumption that BS only knows the statistical channel state information (CSI) between STAR-RIS and the wardens. Subsequently, an optimization problem is formulated with the aim of maximizing the average sum of the covert rate and the minimum secure rate while ensuring the covert requirement and quality of service (QoS) for legal users by jointly optimizing the active and passive beamformers. Due to the strong coupling among variables, an iterative algorithm based on the alternating strategy and the semi-definite relaxation (SDR) method is proposed to solve the non-convex optimization problem. Simulation results indicate that the performance of the proposed STAR-RIS-assisted scheme greatly surpasses that of the conventional RIS scheme, which validates the superiority of STAR-RIS in simultaneously implementing PLS and CCs.

In commercial unmanned aerial vehicle (UAV) applications, one of the main restrictions is UAVs' limited battery endurance when executing persistent tasks. With the mature of wireless power transfer (WPT) technologies, by leveraging ground vehicles mounted with WPT facilities on their proofs, we propose a mobile and collaborative recharging scheme for UAVs in an on-demand manner. Specifically, we first present a novel air-ground cooperative UAV recharging framework, where ground vehicles cooperatively share their idle wireless chargers to UAVs and a swarm of UAVs in the task area compete to get recharging services. Considering the mobility dynamics and energy competitions, we formulate an energy scheduling problem for UAVs and vehicles under practical constraints. A fair online auction-based solution with low complexity is also devised to allocate and price idle wireless chargers on vehicular proofs in real time. We rigorously prove that the proposed scheme is strategy-proof, envy-free, and produces stable allocation outcomes. The first property enforces that truthful bidding is the dominant strategy for participants, the second ensures that no user is better off by exchanging his allocation with another user when the auction ends, while the third guarantees the matching stability between UAVs and UGVs. Extensive simulations validate that the proposed scheme outperforms benchmarks in terms of energy allocation efficiency and UAV's utility., Comment: Accepted by China Communications in June 2023

With the widespread use of large artificial intelligence (AI) models such as ChatGPT, AI-generated content (AIGC) has garnered increasing attention and is leading a paradigm shift in content creation and knowledge representation. AIGC uses generative large AI algorithms to assist or replace humans in creating massive, high-quality, and human-like content at a faster pace and lower cost, based on user-provided prompts. Despite the recent significant progress in AIGC, security, privacy, ethical, and legal challenges still need to be addressed. This paper presents an in-depth survey of working principles, security and privacy threats, state-of-the-art solutions, and future challenges of the AIGC paradigm. Specifically, we first explore the enabling technologies, general architecture of AIGC, and discuss its working modes and key characteristics. Then, we investigate the taxonomy of security and privacy threats to AIGC and highlight the ethical and societal implications of GPT and AIGC technologies. Furthermore, we review the state-of-the-art AIGC watermarking approaches for regulatable AIGC paradigms regarding the AIGC model and its produced content. Finally, we identify future challenges and open research directions related to AIGC., Comment: 20 pages, 6 figures, 4 tables

Due to the limited battery and computing resource, offloading unmanned aerial vehicles (UAVs)' computation tasks to ground infrastructure, e.g., vehicles, is a fundamental framework. Under such an open and untrusted environment, vehicles are reluctant to share their computing resource unless provisioning strong incentives, privacy protection, and fairness guarantee. Precisely, without strategy-proofness guarantee, the strategic vehicles can overclaim participation costs so as to conduct market manipulation. Without the fairness provision, vehicles can deliberately abort the assigned tasks without any punishments, and UAVs can refuse to pay by the end, causing an exchange dilemma. Lastly, the strategy-proofness and fairness provision typically require transparent payment/task results exchange under public audit, which may disclose sensitive information of vehicles and make the privacy preservation a foremost issue. To achieve the three design goals, we propose SEAL, an integrated framework to address strategy-proof, fair, and privacy-preserving UAV computation offloading. SEAL deploys a strategy-proof reverse combinatorial auction mechanism to optimize UAVs' task offloading under practical constraints while ensuring economic-robustness and polynomial-time efficiency. Based on smart contracts and hashchain micropayment, SEAL implements a fair on-chain exchange protocol to realize the atomic completion of batch payments and computing results in multi-round auctions. In addition, a privacy-preserving off-chain auction protocol is devised with the assistance of the trusted processor to efficiently protect vehicles' bid privacy. Using rigorous theoretical analysis and extensive simulations, we validate that SEAL can effectively prevent vehicles from manipulating, ensure privacy protection and fairness, improve the offloading efficiency., Comment: Accepted by IEEE Transactions on Information Forensics and Security (IEEE TIFS)

In order to save computing power yet enhance safety, there is a strong intention for autonomous vehicles (AVs) in future to drive collaboratively by sharing sensory data and computing results among neighbors. However, the intense collaborative computing and data transmissions among unknown others will inevitably introduce severe security concerns. Aiming at addressing security concerns in future AVs, in this paper, we develop SPAD, a secured framework to forbid free-riders and {promote trustworthy data dissemination} in collaborative autonomous driving. Specifically, we first introduce a publish/subscribe framework for inter-vehicle data transmissions{. To defend against free-riding attacks,} we formulate the interactions between publisher AVs and subscriber AVs as a vehicular publish/subscribe game, {and incentivize AVs to deliver high-quality data by analyzing the Stackelberg equilibrium of the game. We also design a reputation evaluation mechanism in the game} to identify malicious AVs {in disseminating fake information}. {Furthermore, for} lack of sufficient knowledge on parameters of {the} network model and user cost model {in dynamic game scenarios}, a two-tier reinforcement learning based algorithm with hotbooting is developed to obtain the optimal {strategies of subscriber AVs and publisher AVs with free-rider prevention}. Extensive simulations are conducted, and the results validate that our SPAD can effectively {prevent free-riders and enhance the dependability of disseminated contents,} compared with conventional schemes.

Task allocation plays a vital role in multi-robot autonomous cleaning systems, where multiple robots work together to clean a large area. However, most current studies mainly focus on deterministic, single-task allocation for cleaning robots, without considering hybrid tasks in uncertain working environments. Moreover, there is a lack of datasets and benchmarks for relevant research. In this paper, to address these problems, we formulate multi-robot hybrid-task allocation under the uncertain cleaning environment as a robust optimization problem. Firstly, we propose a novel robust mixed-integer linear programming model with practical constraints including the task order constraint for different tasks and the ability constraints of hybrid robots. Secondly, we establish a dataset of \emph{100} instances made from floor plans, each of which has 2D manually-labeled images and a 3D model. Thirdly, we provide comprehensive results on the collected dataset using three traditional optimization approaches and a deep reinforcement learning-based solver. The evaluation results show that our solution meets the needs of multi-robot cleaning task allocation and the robust solver can protect the system from worst-case scenarios with little additional cost. The benchmark will be available at {https://github.com/iamwangyabin/Multi-robot-Cleaning-Task-Allocation}.

By interacting, synchronizing, and cooperating with its physical counterpart in real time, digital twin is promised to promote an intelligent, predictive, and optimized modern city. Via interconnecting massive physical entities and their virtual twins with inter-twin and intra-twin communications, the Internet of digital twins (IoDT) enables free data exchange, dynamic mission cooperation, and efficient information aggregation for composite insights across vast physical/virtual entities. However, as IoDT incorporates various cutting-edge technologies to spawn the new ecology, severe known/unknown security flaws and privacy invasions of IoDT hinders its wide deployment. Besides, the intrinsic characteristics of IoDT such as \emph{decentralized structure}, \emph{information-centric routing} and \emph{semantic communications} entail critical challenges for security service provisioning in IoDT. To this end, this paper presents an in-depth review of the IoDT with respect to system architecture, enabling technologies, and security/privacy issues. Specifically, we first explore a novel distributed IoDT architecture with cyber-physical interactions and discuss its key characteristics and communication modes. Afterward, we investigate the taxonomy of security and privacy threats in IoDT, discuss the key research challenges, and review the state-of-the-art defense approaches. Finally, we point out the new trends and open research directions related to IoDT., Comment: 21 pages, 7 figures

Social metaverse is a shared digital space combining a series of interconnected virtual worlds for users to play, shop, work, and socialize. In parallel with the advances of artificial intelligence (AI) and growing awareness of data privacy concerns, federated learning (FL) is promoted as a paradigm shift towards privacy-preserving AI-empowered social metaverse. However, challenges including privacy-utility tradeoff, learning reliability, and AI model thefts hinder the deployment of FL in real metaverse applications. In this paper, we exploit the pervasive social ties among users/avatars to advance a social-aware hierarchical FL framework, i.e., SocialFL for a better privacy-utility tradeoff in the social metaverse. Then, an aggregator-free robust FL mechanism based on blockchain is devised with a new block structure and an improved consensus protocol featured with on/off-chain collaboration. Furthermore, based on smart contracts and digital watermarks, an automatic federated AI (FedAI) model ownership provenance mechanism is designed to prevent AI model thefts and collusive avatars in social metaverse. Experimental findings validate the feasibility and effectiveness of proposed framework. Finally, we envision promising future research directions in this emerging area., Comment: Accepted by Internet of Things Magazine in 23-May 2023

To prevent implicit privacy disclosure in sharing gradients among data owners (DOs) under federated learning (FL), differential privacy (DP) and its variants have become a common practice to offer formal privacy guarantees with low overheads. However, individual DOs generally tend to inject larger DP noises for stronger privacy provisions (which entails severe degradation of model utility), while the curator (i.e., aggregation server) aims to minimize the overall effect of added random noises for satisfactory model performance. To address this conflicting goal, we propose a novel dynamic privacy pricing (DyPP) game which allows DOs to sell individual privacy (by lowering the scale of locally added DP noise) for differentiated economic compensations (offered by the curator), thereby enhancing FL model utility. Considering multi-dimensional information asymmetry among players (e.g., DO's data distribution and privacy preference, and curator's maximum affordable payment) as well as their varying private information in distinct FL tasks, it is hard to directly attain the Nash equilibrium of the mixed-strategy DyPP game. Alternatively, we devise a fast reinforcement learning algorithm with two layers to quickly learn the optimal mixed noise-saving strategy of DOs and the optimal mixed pricing strategy of the curator without prior knowledge of players' private information. Experiments on real datasets validate the feasibility and effectiveness of the proposed scheme in terms of faster convergence speed and enhanced FL model utility with lower payment costs., Comment: Accepted by IEEE ICC2023

A key feature of federated learning (FL) is to preserve the data privacy of end users. However, there still exist potential privacy leakage in exchanging gradients under FL. As a result, recent research often explores the differential privacy (DP) approaches to add noises to the computing results to address privacy concerns with low overheads, which however degrade the model performance. In this paper, we strike the balance of data privacy and efficiency by utilizing the pervasive social connections between users. Specifically, we propose SCFL, a novel Social-aware Clustered Federated Learning scheme, where mutually trusted individuals can freely form a social cluster and aggregate their raw model updates (e.g., gradients) inside each cluster before uploading to the cloud for global aggregation. By mixing model updates in a social group, adversaries can only eavesdrop the social-layer combined results, but not the privacy of individuals. We unfold the design of SCFL in three steps.i) Stable social cluster formation. Considering users' heterogeneous training samples and data distributions, we formulate the optimal social cluster formation problem as a federation game and devise a fair revenue allocation mechanism to resist free-riders. ii) Differentiated trust-privacy mapping}. For the clusters with low mutual trust, we design a customizable privacy preservation mechanism to adaptively sanitize participants' model updates depending on social trust degrees. iii) Distributed convergence}. A distributed two-sided matching algorithm is devised to attain an optimized disjoint partition with Nash-stable convergence. Experiments on Facebook network and MNIST/CIFAR-10 datasets validate that our SCFL can effectively enhance learning utility, improve user payoff, and enforce customizable privacy protection., Comment: This paper has been accepted by IEEE/ACM Transactions on Networking in March 2024

This paper focuses on the prevalent performance imbalance in the stages of incremental learning. To avoid obvious stage learning bottlenecks, we propose a brand-new stage-isolation based incremental learning framework, which leverages a series of stage-isolated classifiers to perform the learning task of each stage without the interference of others. To be concrete, to aggregate multiple stage classifiers as a uniform one impartially, we first introduce a temperature-controlled energy metric for indicating the confidence score levels of the stage classifiers. We then propose an anchor-based energy self-normalization strategy to ensure the stage classifiers work at the same energy level. Finally, we design a voting-based inference augmentation strategy for robust inference. The proposed method is rehearsal free and can work for almost all continual learning scenarios. We evaluate the proposed method on four large benchmarks. Extensive results demonstrate the superiority of the proposed method in setting up new state-of-the-art overall performance. \emph{Code is available at} \url{https://github.com/iamwangyabin/ESN}., Comment: This is the accepted version of the Paper & Supp to appear in AAAI 2023. Please cite the final published version. Code is available at https://github.com/iamwangyabin/ESN

Unmanned aerial vehicles (UAVs) have the potential to establish flexible and reliable emergency networks in disaster sites when terrestrial communication infrastructures go down. Nevertheless, potential security threats may occur on UAVs during data transmissions due to the untrusted environment and open-access UAV networks. Moreover, UAVs typically have limited battery and computation capacity, making them unaffordable for heavy security provisioning operations when performing complicated rescue tasks. In this paper, we develop RescueChain, a secure and efficient information sharing scheme for UAV-assisted disaster rescue. Specifically, we first implement a lightweight blockchain-based framework to safeguard data sharing under disasters and immutably trace misbehaving entities. A reputation-based consensus protocol is devised to adapt the weakly connected environment with improved consensus efficiency and promoted UAVs' honest behaviors. Furthermore, we introduce a novel vehicular fog computing (VFC)-based off-chain mechanism by leveraging ground vehicles as moving fog nodes to offload UAVs' heavy data processing and storage tasks. To offload computational tasks from the UAVs to ground vehicles having idle computing resources, an optimal allocation strategy is developed by choosing payoffs that achieve equilibrium in a Stackelberg game formulation of the allocation problem. For lack of sufficient knowledge on network model parameters and users' private cost parameters in practical environment, we also design a two-tier deep reinforcement learning-based algorithm to seek the optimal payment and resource strategies of UAVs and vehicles with improved learning efficiency. Simulation results show that RescueChain can effectively accelerate consensus process, improve offloading efficiency, reduce energy consumption, and enhance user payoffs., Comment: Accepted by IEEE/ACM Transactions on Networking (ToN)

The proliferation of unmanned aerial vehicles (UAVs) opens up new opportunities for on-demand service provisioning anywhere and anytime, but also exposes UAVs to a variety of cyber threats. Low/medium interaction honeypots offer a promising lightweight defense for actively protecting mobile Internet of things, particularly UAV networks. While previous research has primarily focused on honeypot system design and attack pattern recognition, the incentive issue for motivating UAV's participation (e.g., sharing trapped attack data in honeypots) to collaboratively resist distributed and sophisticated attacks remains unexplored. This paper proposes a novel game-theoretical collaborative defense approach to address optimal, fair, and feasible incentive design, in the presence of network dynamics and UAVs' multi-dimensional private information (e.g., valid defense data (VDD) volume, communication delay, and UAV cost). Specifically, we first develop a honeypot game between UAVs and the network operator under both partial and complete information asymmetry scenarios. The optimal VDD-reward contract design problem with partial information asymmetry is then solved using a contract-theoretic approach that ensures budget feasibility, truthfulness, fairness, and computational efficiency. In addition, under complete information asymmetry, we devise a distributed reinforcement learning algorithm to dynamically design optimal contracts for distinct types of UAVs in the time-varying UAV network. Extensive simulations demonstrate that the proposed scheme can motivate UAV's cooperation in VDD sharing and improve defensive effectiveness, compared with conventional schemes., Comment: Accepted Aug. 28, 2023 by IEEE Transactions on Information Forensics & Security. arXiv admin note: text overlap with arXiv:2209.13815

The proliferation of unmanned aerial vehicles (UAVs) opens up new opportunities for on-demand service provisioning anywhere and anytime, but it also exposes UAVs to various cyber threats. Low/medium-interaction honeypot is regarded as a promising lightweight defense to actively protect mobile Internet of things, especially UAV networks. Existing works primarily focused on honeypot design and attack pattern recognition, the incentive issue for motivating UAVs' participation (e.g., sharing trapped attack data in honeypots) to collaboratively resist distributed and sophisticated attacks is still under-explored. This paper proposes a novel game-based collaborative defense approach to address optimal, fair, and feasible incentive mechanism design, in the presence of network dynamics and UAVs' multi-dimensional private information (e.g., valid defense data (VDD) volume, communication delay, and UAV cost). Specifically, we first develop a honeypot game between UAVs under both partial and complete information asymmetry scenarios. We then devise a contract-theoretic method to solve the optimal VDD-reward contract design problem with partial information asymmetry, while ensuring truthfulness, fairness, and computational efficiency. Furthermore, under complete information asymmetry, we devise a reinforcement learning based distributed method to dynamically design optimal contracts for distinct types of UAVs in the fast-changing network. Experimental simulations show that the proposed scheme can motivate UAV's collaboration in VDD sharing and enhance defensive effectiveness, compared with existing solutions., Comment: Accepted by IEEE Globecom2022

In this paper, we propose a new agency-guided semi-supervised counting approach. First, we build a learnable auxiliary structure, namely the density agency to bring the recognized foreground regional features close to corresponding density sub-classes (agents) and push away background ones. Second, we propose a density-guided contrastive learning loss to consolidate the backbone feature extractor. Third, we build a regression head by using a transformer structure to refine the foreground features further. Finally, an efficient noise depression loss is provided to minimize the negative influence of annotation noises. Extensive experiments on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised counting methods by a large margin. Code is available., Comment: This is the accepted version of the Paper & Supp to appear in ACM MM 2022. Please cite the final published version. Code is available at https://github.com/LoraLinH/Semi-supervised-Crowd-Counting-via-Density-Agency

Proof of work (PoW), as the representative consensus protocol for blockchain, consumes enormous amounts of computation and energy to determine bookkeeping rights among miners but does not achieve any practical purposes. To address the drawback of PoW, we propose a novel energy-recycling consensus mechanism named platform-free proof of federated learning (PF-PoFL), which leverages the computing power originally wasted in solving hard but meaningless PoW puzzles to conduct practical federated learning (FL) tasks. Nevertheless, potential security threats and efficiency concerns may occur due to the untrusted environment and miners' self-interested features. In this paper, by devising a novel block structure, new transaction types, and credit-based incentives, PF-PoFL allows efficient artificial intelligence (AI) task outsourcing, federated mining, model evaluation, and reward distribution in a fully decentralized manner, while resisting spoofing and Sybil attacks. Besides, PF-PoFL equips with a user-level differential privacy mechanism for miners to prevent implicit privacy leakage in training FL models. Furthermore, by considering dynamic miner characteristics (e.g., training samples, non-IID degree, and network delay) under diverse FL tasks, a federation formation game-based mechanism is presented to distributively form the optimized disjoint miner partition structure with Nash-stable convergence. Extensive simulations validate the efficiency and effectiveness of PF-PoFL., Comment: Accepted by IEEE Journal on Selected Areas in Communications

There has been an increasing interest in modeling continuous-time dynamics of temporal graph data. Previous methods encode time-evolving relational information into a low-dimensional representation by specifying discrete layers of neural networks, while real-world dynamic graphs often vary continuously over time. Hence, we propose Continuous Temporal Graph Networks (CTGNs) to capture the continuous dynamics of temporal graph data. We use both the link starting timestamps and link duration as evolving information to model the continuous dynamics of nodes. The key idea is to use neural ordinary differential equations (ODE) to characterize the continuous dynamics of node representations over dynamic graphs. We parameterize ordinary differential equations using a novel graph neural network. The existing dynamic graph networks can be considered as a specific discretization of CTGNs. Experiment results on both transductive and inductive tasks demonstrate the effectiveness of our proposed approach over competitive baselines.

This paper investigates physical layer security (PLS) in the intelligent reflecting surface (IRS)-assisted multiple-user uplink channel. Since the instantaneous eavesdropper's channel state information (CSI) is unavailable, the secrecy rate can not be measured. In this case, existing investigations usually focus on the maximization of the minimum (max-min) of signal to interference plus noise power ratio (SINRs) among multiple users, and do not consider secrecy outage probability caused by eavesdroppers. In this paper, we first formulate the minimization of the maximum (min-max) secrecy outage probability among multiple users. The formulated problem is solved by alternately optimizing receiving matrix and phase shift matrix. Simulations demonstrate that the maximum secrecy outage probability is significantly reduced with the proposed algorithm compared to max-min SINR strategies, meaning our scheme has a higher security performance.

This article investigates physical layer security (PLS) in reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output multiple-antenna-eavesdropper (MIMOME) channels. Existing researches ignore the problem that secrecy rate can not be calculated if the eavesdropper's instantaneous channel state information (CSI) is unknown. Furthermore, without the secrecy rate expression, beamforming and phase shifter optimization with the purpose of PLS enhancement is not available. To address these problems, we first give the expression of secrecy outage probability for any beamforming vector and phase shifter matrix as the RIS-assisted PLS metric, which is measured based on the eavesdropper's statistical CSI. Then, with the aid of the expression, we formulate the minimization problem of secrecy outage probability that is solved via alternately optimizing beamforming vectors and phase shift matrices. In the case of single-antenna transmitter or single-antenna legitimate receiver, the proposed alternating optimization (AO) scheme can be simplified to reduce computational complexity. Finally, it is demonstrated that the secrecy outage probability is significantly reduced with the proposed methods compared to current RIS-assisted PLS systems.

This paper investigates computation offloading in blockchain-empowered Internet of Things (IoT), where the task data uploading link from sensors to a base station (BS) is protected by intelligent reflecting surface (IRS)-assisted physical layer security (PLS). After receiving task data, the BS allocates computational resources provided by mobile edge computing (MEC) servers to help sensors perform tasks. Existing blockchain-based computation offloading schemes usually focus on network performance improvements, such as energy consumption minimization or latency minimization, and neglect the Gas fee for computation offloading, resulting in the dissatisfaction of high Gas providers. Also, the secrecy rate during the data uploading process can not be measured by a steady value because of the time-varying characteristics of IRS-based wireless channels, thereby computational resources allocation with a secrecy rate measured before data uploading is inappropriate. In this paper, we design a Gas-oriented computation offloading scheme that guarantees a low degree of dissatisfaction of sensors, while reducing energy consumption. Also, we deduce the ergodic secrecy rate of IRS-assisted PLS transmission that can represent the global secrecy performance to allocate computational resources. The simulations show that the proposed scheme has lower energy consumption compared to existing schemes, and ensures that the node paying higher Gas gets stronger computational resources., Comment: arXiv admin note: text overlap with arXiv:2203.01621

Unmanned aerial vehicles (UAVs) can help facilitate cost-effective and flexible service provisioning in future smart cities. Nevertheless, UAV applications generally suffer severe flight time limitations due to constrained onboard battery capacity, causing a necessity of frequent battery recharging or replacement when performing persistent missions. Utilizing wireless mobile chargers, such as vehicles with wireless charging equipment for on-demand self-recharging has been envisioned as a promising solution to address this issue. In this article, we present a comprehensive study of \underline{v}ehicle-assisted \underline{w}ireless rechargeable \underline{U}AV \underline{n}etworks (VWUNs) to promote on-demand, secure, and efficient UAV recharging services. Specifically, we first discuss the opportunities and challenges of deploying VWUNs and review state-of-the-art solutions in this field. We then propose a secure and privacy-preserving VWUN framework for UAVs and ground vehicles based on differential privacy (DP). Within this framework, an online double auction mechanism is developed for optimal charging scheduling, and a two-phase DP algorithm is devised to preserve the sensitive bidding and energy trading information of participants. Experimental results demonstrate that the proposed framework can effectively enhance charging efficiency and security. Finally, we outline promising directions for future research in this emerging field., Comment: Accepted by IEEE Communication Magazine

Metaverse, as an evolving paradigm of the next-generation Internet, aims to build a fully immersive, hyper spatiotemporal, and self-sustaining virtual shared space for humans to play, work, and socialize. Driven by recent advances in emerging technologies such as extended reality, artificial intelligence, and blockchain, metaverse is stepping from science fiction to an upcoming reality. However, severe privacy invasions and security breaches (inherited from underlying technologies or emerged in the new digital ecology) of metaverse can impede its wide deployment. At the same time, a series of fundamental challenges (e.g., scalability and interoperability) can arise in metaverse security provisioning owing to the intrinsic characteristics of metaverse, such as immersive realism, hyper spatiotemporality, sustainability, and heterogeneity. In this paper, we present a comprehensive survey of the fundamentals, security, and privacy of metaverse. Specifically, we first investigate a novel distributed metaverse architecture and its key characteristics with ternary-world interactions. Then, we discuss the security and privacy threats, present the critical challenges of metaverse systems, and review the state-of-the-art countermeasures. Finally, we draw open research directions for building future metaverse systems., Comment: 32 pages, 17 figures, 11 tables. Accepted by IEEE Communications Surveys & Tutorials, 2022

This paper investigates an endogenous security architecture for computation offloading in the Internet of Things (IoT), where the blockchain technology enables the traceability of malicious behaviors, and the task data uploading link from sensors to small base station (SBS) is protected by intelligent reflecting surface (IRS)-assisted physical layer security (PLS). After receiving task data, the SBS allocates computational resources to help sensors perform the task. The existing computation offloading schemes usually focus on network performance improvement, such as energy consumption minimization, and neglect the Gas fee paid by sensors, resulting in the discontent of high Gas payers. Here, we design a Gas-oriented computation offloading scheme that guarantees the degree of satisfaction of sensors, while aiming to reduce energy consumption. Also, we deduce the ergodic secrecy rate of IRS-assisted PLS transmission that can represent the global secrecy performance to allocate computational resources. The simulations show that the proposed scheme ensures that the node paying higher Gas gets stronger computational resources, and just raises $4\%$ energy consumption in comparison with energy consumption minimization schemes.

The emerging autonomous vehicles (AVs) will inevitably revolutionize the transportation systems. This is because of a key feature of AVs; instead of being managed by human drivers as the conventional vehicles, AVs are of the complete capability to manage the driving by themselves. As a result, the futuristic intelligent transportation system (FITS) can be a centrally managed and optimized system with the fully coordinated driving of vehicles, which is impossible by the current transportation systems controlled by humans. In this article, we envision the operation of such FITS when AVs, advanced vehicular networks (VANETs) and artificial intelligence (AI) are adopted. Specifically, we first develop the autonomous vehicular networks (AVNs) based on the advanced development of AVs and heterogeneous vehicular communication technologies to achieve global data collection and real-time data sharing. With this network architecture, we then integrate AVNs and AI based on the intelligent digital twin (IDT) to design the FITS with the target of setting up an accurate and efficient global traffic scheduling system. After that, compared with the conventional schemes, a customized path planning case is studied to evaluate the performance of the proposed FITS. Finally, we highlight the emerging issues related to the FITS for future research.

Visual question answering (VQA) requires joint comprehension of images and natural language questions, where many questions can't be directly or clearly answered from visual content but require reasoning from structured human knowledge with confirmation from visual content. This paper proposes visual knowledge memory network (VKMN) to address this issue, which seamlessly incorporates structured human knowledge and deep visual features into memory networks in an end-to-end learning framework. Comparing to existing methods for leveraging external knowledge for supporting VQA, this paper stresses more on two missing mechanisms. First is the mechanism for integrating visual contents with knowledge facts. VKMN handles this issue by embedding knowledge triples (subject, relation, target) and deep visual features jointly into the visual knowledge features. Second is the mechanism for handling multiple knowledge facts expanding from question and answer pairs. VKMN stores joint embedding using key-value pair structure in the memory networks so that it is easy to handle multiple facts. Experiments show that the proposed method achieves promising results on both VQA v1.0 and v2.0 benchmarks, while outperforms state-of-the-art methods on the knowledge-reasoning related questions., Comment: Supplementary to CVPR 2018 version

This paper focuses on a novel and challenging vision task, dense video captioning, which aims to automatically describe a video clip with multiple informative and diverse caption sentences. The proposed method is trained without explicit annotation of fine-grained sentence to video region-sequence correspondence, but is only based on weak video-level sentence annotations. It differs from existing video captioning systems in three technical aspects. First, we propose lexical fully convolutional neural networks (Lexical-FCN) with weakly supervised multi-instance multi-label learning to weakly link video regions with lexical labels. Second, we introduce a novel submodular maximization scheme to generate multiple informative and diverse region-sequences based on the Lexical-FCN outputs. A winner-takes-all scheme is adopted to weakly associate sentences to region-sequences in the training phase. Third, a sequence-to-sequence learning based language model is trained with the weakly supervised information obtained through the association process. We show that the proposed method can not only produce informative and diverse dense captions, but also outperform state-of-the-art single video captioning methods by a large margin., Comment: To appear in CVPR 2017