Fluid antennas (FAs) have emerged as a promising technology for enhancing the performance of integrated sensing and communication (ISAC) systems owing to their flexible antenna positions. This paper provides a comprehensive review of FA-enabled ISAC for showcasing the significant potential of FAs in enhancing ISAC systems. On this basis, we propose an innovative air-ground collaborative framework that incorporates FAs to tackle complex tasks involving sensing for data acquisition, communication for information exchange, and computation for data processing. In this framework, the collaboration relationship between unmanned aerial vehicles (UAVs) and an FA-equipped remote base station (BS) is explored to complete the complex tasks. Specifically, multiple UAVs sense ground targets by transmitting radar signals. Upon receiving radar echoes, each UAV processes sensing data in collaboration with the BS by offloading a part of the sensing data to the BS. To facilitate cooperation, we utilize the radar estimation rate to characterize sensing performance and design a synergistic algorithm to coordinate the positions of FAs, the receive beamforming of the BS, computation resource allocation, task offloading ratios, and UAV deployment to minimize the average task completion delay in data processing, subject to sensing performance requirements. Simulation results demonstrate that the proposed scheme outperforms several baselines in terms of the average task completion delay.

Space-air-ground integrated Internet of things (IoT) networks can enable seamless global coverage for IoT devices and effectively alleviate the burden on terrestrial IoT data transmission. However, due to the complexity of network architecture and the wide geographical distribution of IoT nodes, significant discrepancies may occur in the timing of control information reception among certain nodes. New challenges arise accordingly for the unified management of multi-dimensional resources and task offloading in the network. To mitigate this, in this paper, we propose a dynamic two time-scales resource management framework that simultaneously takes task types, requirements, and priorities into account. Moreover, quality of experience (QoE) models are designed for the IoT users generating data-transmission and computation-intensive tasks, and an optimization problem is formulated to maximize the overall QoE. Given the multi-scale coupling constraints and mixed-integer program of the formulated problem, we decouple it into two Markov decision process-based subproblems and develop an interactive dual-agent proximal policy optimization algorithm to address them. Numerical results demonstrate the superiority of our proposed algorithm compared to benchmark algorithms.

To support the unprecedented growth of the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Internet of Things</i> (IoT) networks, tremendous data need to be collected by the IoT devices and processed. Due to the limited computing capabilities of IoT devices, part of collected data need to be offloaded to the edge server for further processing. The conventional designs separately considering sensing, communication and computation processes lead to severe wastes of radio, energy, and computation resources. To overcome this drawback, an <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">integrated sensing-communication-computation</i> (ISCC) design is proposed in this paper, which aims at realizing energy efficient data processing by jointly determining the data offloading ratio together with the sensing and offloading rates according to the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">central processing units</i> (CPU) profiles of IoT devices and servers. To deal with the resultant non-trivial optimization problem, the case with full-utilization of the server's CPU resource is considered, where the data offloading ratio is directly determined by the server's CPU profile, and the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">string-pulling</i> (SP) algorithms are proposed to obtain the optimal sensing and offloading rates. As for the case with under-utilization of the server's CPU resource, a master-slave solving approach is proposed, where the master problem for optimizing the data offloading ratio can be solved by sub-gradient method, while the slave problem for optimizing the sensing and offloading rates can be solved by SP algorithms. The above solving approaches are further modified to account for the case with sensing busy time at which no data can be sensed by the IoT device. Simulations are conducted to verify the effectiveness of the proposed algorithms.

Online-to-Offline (O2O) e-commerce services and their users confront a spectrum of fraud risks, where financial identity theft is prevalent and severe. However, current approaches are inadequate to cover such fraud. To address this problem, we consider both environmental entity interactions and activity sequences to model more granular user behaviors. According to our preliminary study, we discovered that fraudulent users exhibit high aggregations of various environmental entities and fraudulent individuals using the same personal ID that features diverse interactions with different environmental entities. We further investigate the abnormal behaviors of individual fraudsters. Motivated by these discoveries, we propose a deep learning-based behavior modeling framework named EnvIT to capture the above behavior patterns. Therefore, EnvIT is sufficiently general to learn user representations for various e-commerce fraud situations. Extensive experiments are conducted on two real-world datasets provided by Meituan and Vesta, respectively. Extensive results demonstrate the superiority of our method, with a 0.17%-13.50% improvement in AUC and 1.13%-22.57% in R@90%P on the Meituan dataset, and a 0.71%-11.94% improvement in AUC and 2.99%-21.19% in R@90%P on the Vesta dataset, respectively.

The 6 G Computing Power Network (CPN) is envisioned to orchestrate vast, distributed computing resources for future intelligent applications. However, achieving efficient, trusted, and privacy-preserving computing resource sharing in this decentralized environment poses significant challenges. To address these intertwined issues, this article proposes a holistic blockchain and evolutionary algorithm-based computing resource sharing (BECS) mechanism. BECS is designed to dynamically and adaptively balance task offloading among computing resources within the 6 G CPN, thereby enhancing resource utilization. We model computing resource sharing as a multi-objective optimization problem, aiming to navigate these trade-offs. To tackle this NP-hard problem, we devise a kernel-distance-based dominance relation and incorporate it into the Non-dominated Sorting Genetic Algorithm III (NSGA-III), thereby significantly enhancing population diversity. In addition, we propose a pseudonym scheme based on zero-knowledge proofs to protect user privacy during computing resource sharing. Finally, security analysis and simulation results demonstrate that BECS can effectively leverage all computing resources in the 6 G CPN, thereby significantly improving resource utilization while preserving user privacy.

The application of wireless sensor networks (WSNs) in underground or underwater regions is becoming increasingly prevalent. This specific type of WSNs are referred to as wireless weak-link sensor networks (WWSNs), whose key distribution is identified as a prerequisite for ensuring network security. However, due to the fragile links of WWSNs, it is not feasible to directly transfer existing authenticated Diffie-Hellman (ADH) protocols from traditional WSNs to WWSNs. To address this challenge, we propose a disconnection-resistant authenticated Diffie-Hellman protocol (D-ADH) for key distribution in WWSNs. For mitigating the adverse impact of fragile links, we significantly reduce the number of node interactions in existing ADH protocols by having the sensor node use fixed negotiation public keys. Each sensor node only needs to receive the broadcast message of the base station on a single occasion to generate the session key. The results of simulation experiments and security analysis demonstrate that the proposed D-ADH protocol exhibits the lowest energy consumption, the longest network lifetime, the highest probability of successful key distribution and good network scalability compared to the state-of-the-art protocols, while maintaining an acceptable middle level security.

This article explores various approaches to enhance the physical layer security performance of cooperative non-orthogonal multiple access (CNOMA) system, in scenarios involving multiple non-colluding or colluding eavesdroppers, taking into account residual hardware impairment (RHI) and imperfect successive interference cancellation conditions. Firstly, we propose a jamming-assisted (JA) framework for enhancing the physical layer security performance and derive analytical expressions for the secrecy outage probabilities (SOPs) of the downlink users and the system SOP (SSOP) of the CNOMA network for both JA and no-jammer (NJ) scenarios. It is illustrated that the proposed JA framework offers several key benefits: (i) a significant reduction in the SOPs and SSOP, (ii) a notable increase in system secrecy throughput (SST) and secrecy energy efficiency (SEE) for the network, and (iii) a complete alleviation of the zero-diversity order problem, if the transceivers are free of RHI. Following this, the optimal power allocation coefficients for the users at the base station and at the relay that independently as well as jointly minimize the SSOP of the JA-CNOMA network are determined. We demonstrate that the proposed approach results in: (i) considerable decrease of SSOP and SOPs and (ii) significant enhancement of SST and SEE of the JA-CNOMA network, compared to equal/random power allocation methods.

In recent years, federated learning-based network traffic classification has emerged as a promising Artificial Intelligence (AI) approach for encrypted traffic identification, enabling accurate classification while preserving data privacy. To meet the rising demand for the right to be forgotten, Federated Machine Unlearning (FMU) has been introduced as an AI-driven forget ting paradigm. However, conventional FMU methods overlook silent applications removed due to guideline violations, resulting in reduced classifier stability and limited aggregation scalability. To address these challenges, this paper proposes FedUnSilApp, short for FMU for silent applications, a novel FMU framework that integrates a learning module, a forgetting module, and a scalable aggregation strategy. In particular, the forgetting module prunes neurons associated with silent applications in the classifier, minimizing their residual influence. The scalable aggregation strategy separately processes discriminative layers of clients requesting forgetting and those of other clients, thereby enhancing both stability and scalability of the global model. In addition, FedUnSilApp is applied to the real-world scenario of encrypted network traffic classification, enabling compliance with deletion requests while maintaining robust classification performance. The effectiveness of FedUnSilApp is validated through experiments, which show that FedUnSilApp outperforms state-of-the-art methods, improving accuracy by over 6% on the NJUPT dataset.

In sensor networks, due to inevitable sensor faults, malfunctions, or deliberate attacks, sensors may transmit erroneous, inaccurate, or misleading data, thereby degrading overall system performance. To address this issue, an effective approach is to assign reputation scores to sensors based on their trustworthiness, historical performance, or reliability. In this paper, the reputation-based distributed filtering (RBDF) problem is considered for a class of stochastic nonlinear systems over sensor networks with network-induced quantization. A reputation mechanism is employed to mitigate the adverse effects caused by noisy, faulty, or malicious sensors. Specifically, reputations are allocated by each sensor to the data received from its neighbors, ensuring that abnormal data are assigned smaller reputation values and may even be discarded. For the first time, a recursive RBDF algorithm is proposed, wherein an upper bound of the filtering error covariance (UBFEC) is derived by solving two matrix equations. Subsequently, the filter gain is determined by minimizing the trace of UBFEC at each step. Furthermore, a sufficient condition is presented to ensure the uniform boundedness of the filtering error dynamics. Finally, a simulation example is provided to verify the feasibility and validity of the developed RBDF algorithm.

Multi-view clustering (MVC) has gained attention for its ability to efficiently handle complex high-dimensional data. Many existing MVC methods rely on a technique known as Nonnegative Matrix Factorization (NMF). Among these, Symmetric Nonnegative Matrix Factorization (SNMF) notably stands out for its ability to reduce dimensionality and provide easily interpretable representations. However, existing research highlights several challenges associated with SNMF. Firstly, it often necessitates the manual creation of the similarity matrix, which can be effort-intensive. Additionally, SNMF intrinsically employs an unsupervised learning approach, thus inherently neglecting the potential utility of label information. Lastly, while it concentrates on identifying shared information within multi-view data, it tends to overlook the valuable insights that different views might individually present. To overcome these limitations, we propose a novel semi-supervised multi-view clustering framework, termed Semi-supervised Adaptive Symmetric NMF (SSA-SNMF), which integrates adaptive learning and supervision into the SNMF model. The proposed method incorporates three essential components into its objective function: (1) adaptive similarity matrix construction to automatically capture data relationships, (2) integration of pairwise constraint information to leverage available supervision, and (3) a fusion mechanism that balances complementary and consensus information across views. We also derive an efficient optimization algorithm with convergence guarantees. Experimental results on six benchmark datasets show that SSA-SNMF consistently outperforms six state-of-the-art methods, demonstrating its effectiveness and robustness for multi-view clustering tasks.