Movable antenna (MA) technology provides a promising avenue for actively shaping wireless channels through dynamic antenna positioning, thereby enabling electromagnetic radiation reconstruction to enhance physical layer security (PLS). However, its practical deployment is hindered by two major challenges: the high computational complexity of real-time optimization and acritical temporal mismatch between slow mechanical movement and rapid channel variations. Although data-driven methods have been introduced to alleviate online optimization burdens, they are still constrained by suboptimal training labels derived from conventional solvers or high sample complexity in reinforcement learning. More importantly, existing learning-based approaches often overlook communication-specific domain knowledge—particularly the asymmetric roles and adversarial interactions between legitimate users and eavesdroppers, which are fundamental to PLS. To address these issues, this paper reformulates the MA positioning problem as a predictive task and introduces RoleAware-MAPP, a novel Transformer-based framework that incorporates domain knowledge through three key components: role-aware embeddings that model user-specific intentions, physics-informed semantic features that encapsulate channel propagation characteristics, and a composite loss function that strategically prioritizes secrecy performance over mere geometric accuracy. Extensive simulations under 3GPP-compliant scenarios show that RoleAware-MAPP achieves an average secrecy rate of 0.3606 bps/Hz and a Secrecy Performance Coverage Probability (SPSC) of 79.26%,outperforming the state-of-the-art predictive baseline by 35.5% and 6.73 percentage points, respectively, while maintaining robust performance across diverse user velocities and noise conditions.

Mobile Edge CrowdSensing (MECS) based on Federated Learning (FL) has attracted widespread attention as an intelligent data collection and processing approach. FL trains the global model through aggregating local models of participants without requiring the exchange of raw data. However, directly sharing local models is vulnerable to backdoor attacks launched by adversaries. What's worse, malicious server may collude with participants to manipulate the parameter updating of models and even compromise the accuracy of whole system. To address these challenges, this paper proposes a Privacy-Enhanced Federated Learning (PEFL) framework for MECS with the aim of resisting both backdoor and collusion attacks. In PEFL, a Backdoor Resistant Privacy-Enhanced Aggregation (BRPEA) mechanism with the Differential Privacy-Enhanced Exponential (DPEE) method is developed to perturb local models of participants. Clustering and clipping techniques are also designed in BRPEA to effectively distinguish backdoor models from the benign local models, which eliminate the influence of local models deviation and optimize the noise introduced by differential privacy. Furthermore, a Collusion Resistant Privacy-Preserving Aggregation (CRPEA) mechanism is studied. CRPEA can avoid the collusion between servers and participants and prevent the privacy of local models from being leaked. The theoretical analysis proves the security of proposed PEFL framework and the simulation experiments demonstrate that PEFL can not only ensure the aggregation accuracy of encrypted models but provide robustness against both backdoor and collusion attacks.

The task offloading technology plays a vital role in the Internet of Vehicles (IoV) by satisfying diversified vehicular demands, such as energy consumption and processing delay of computing tasks. Unlike the current related works, which not only ignored wireless interference when making information exchange, but also overlooked the available resources of parked and moving vehicles, this paper proposes a comprehensive solution. First, we model vehicle speed using a truncated Gaussian distri bution, replacing simplistic average speed models in prior studies. Wireless interference in V2V/V2I communications significantly impacts communication quality and reliability, leading to packet loss, increased latency, and reduced throughput. For instance, in high-density traffic scenarios, interference can disrupt com munication links, hindering effective task offloading. Next, by incorporating wireless interference and effective communication duration in V2V and RSUs, we propose an analytical framework for task offloading that jointly optimizes energy consumption and processing delay, leveraging resources from parked/moving vehicles and RSUs. Furthermore, inspired by the Multi-Agent Deep Deterministic Policy Gradient (MADDPG), we design an Interference-Aware Multi-Agent Deep Deterministic Policy Gradient (IA-MADDPG) algorithm. The algorithm ensures resource load balancing while reducing energy consumption and latency, and improves the task offloading completion rate. Simulations validate the effectiveness of IA-MADDPG, demonstrating supe rior convergence speed, energy efficiency, and latency reduction compared to existing methods.

Integrated sensing and communication (ISAC) plays a crucial role in the Internet of Vehicles (IoV), serving as a key factor in enhancing driving safety and traffic efficiency. To address the security challenges of the confidential information transmission caused by the inherent openness nature of wireless medium, different from current physical layer security methods, which depends on the additional communication interference costing extra power resources, in this paper, we investigate a novel physical layer security solution, under which the inherent radar sensing interference of the vehicles is utilized to secure wireless communications. To measure the performance of physical layer security methods in ISAC-based IoV systems, we first define an improved security performance metric called by transmission reliability and sensing accuracy based secrecy rate (TRSA_SR), and derive closed-form expressions of connection outage probability (COP), secrecy outage probability (SOP), success ranging probability (SRP) for evaluating transmission reliability, security and sensing accuracy, respectively. Furthermore, we formulate an optimization problem to maximize the TRSA_SR by utilizing radar sensing interference and joint design of the communication duration, transmission power and straight trajectory of the legitimate transmitter. Finally, the non-convex feature of formulated problem is solved through the problem decomposition and alternating optimization. Simulations indicate that the sensing interference utilization, combined with joint design of transmission power and straight trajectory of the transmitter, achieves a secrecy rate of 3.92bps/Hz for different noise powers for the case of perfect channel state information (CSI). The proposed method maintains robustness, achieving a 60.17% improvement of TRSA_SR under unavailable CSI and location information of the Eve.

Task offloading technology plays a crucial role in the Internet of Vehicles (IoV) by minimizing processing delays through the joint optimization of heterogeneous computing resources supported by vehicles, roadside units (RSUs), and macro base stations (MBSs). Previous works have often ignored the wireless interference during the exchange and sharing of task data. Additionally, the potential for vehicles with similar driving behaviors to form vehicle platooning (VEH-PLA) and effectively integrate individual vehicle resources has not been adequately addressed. Furthermore, as a novel resource management paradigm, VEH-PLA should consider task categorization since vehicles within a VEH-PLA may have identical task offloading requestsan aspect that has also received insufficient attention. In this paper, considering wireless interference, vehicle mobility, VEH-PLA, and task categorization, we propose four task offloading models aimed at minimizing processing delays. By utilizing centralized training and decentralized execution (CTDE) based on multi-agent deep reinforcement learning (MADRL), we present a task offloading decision-making method to find the global optimal offloading decision. This results in significant enhancements in resource load balancing and reductions in processing delays. Finally, simulations validate that the proposed method significantly outperforms traditional task offloading approaches in terms of minimizing processing delays while maintaining balanced resource utilization.

In wireless networks, route transmission can be accomplished, and the system's long-term channel capacity can be increased by leveraging the collaboration among numerous relay nodes. While earlier relay selection methods computed all signal-to-noise ratios before selection, they proved to be ineffective. This study addresses the relay selection issue in wireless collaborative communication by employing a deep reinforcement learning (DRL)-based relay selection technique. Initially, this study examines the collaborative communication process of wireless communication networks as a markov decision process (MDP). Subsequently, it proposes a relay selection technique utilizing entropy proximal policy optimization (EPPO), which incorporates policy entropy. The optimal policy is established by interacting with the environment to select the best relay from among numerous relays. Ultimately, EPPO is compared to the original proximal policy optimization (PPO) algorithm, the Deep Q-Network (DQN) algorithm, and a random relay selection scheme under the premise of unknown instantaneous channel state information (CSI). The network performance is evaluated in terms of system capacity and outage probability. The results of the simulation experiment demonstrate that EPPO outperforms current solutions in these areas.

Data aggregation (DA) plays an important role in the context of Internet of Things (IoT). Although some favorable solutions have been proposed to improve the performances of DA, the complex collusion attacks are often ignored and may produce more serious negative impact on aggregation accuracy. In this article, we design a novel dynamic robust iterative filtering (DRIF) mechanism to enhance the quality of service of IoT applications and improve the vulnerability of DA to the collusion attack. First, the initial reputations based on the maximum likelihood estimation are assigned to sensor nodes in order to resist the collusion attack. Second, the sensor nodes obtain the aggregation result through iterative filtering so as to ensure the accuracy of DA. Especially, a weight updating scheme is proposed to eliminate the negative effect of the accidental anomaly or collusion nodes. Finally, the simulation study indicates that the proposed DRIF mechanism is effective and it can achieve a higher accuracy in the presence of complex dynamic collusion attacks.

Ultra-reliable and low-latency communication (uRLLC) plays an important role in the development of 5G-advanced and 6G wireless networks. Combining unmanned aerial vehicles (UAVs) with non-orthogonal multiple access (NOMA) offers a promising solution to achieve improved reliability and lower latency. This is made possible by enabling line-of-sight (LoS) links and concurrent transmissions through the use of UAVs and NOMA, respectively. However, because of the inherent openness of wireless channel, uRLLC faces the security challenges against being eavesdropped. Physical Layer Security (PLS) has been proposed as an efficient method to secure uRLLC, since it uses only the properties of wireless channels (such as fading, interference, and noise). Although the potential benefits of NOMA-UAV provide a better coverage for ground users, it remains a significant challenge since it may provide a LoS link to eavesdroppers. Therefore, in this paper, we investigate the security and reliability performance of UAV and NOMA based uRLLC scenario, under which UAV serves two different types of users with different needs, i.e., secret users and public users. By using stochastic geometry tools, we derive the closed-form expression of the secrecy rate, an important metric in the study of PLS. Additionally, the secure performance is enhanced by maximizing the secrecy rate through optimizing the hovering height and power assignment of UAV. It should be noted that the hovering position is optimized via power allocation when there is only one secret user. Evaluations demonstrate the effectiveness and correctness of our theoretical analysis.

Deep convolutional neural networks (CNNs) have achieved impressive performance in medical image segmentation; however, their performance could degrade significantly when being deployed to unseen data with heterogeneous characteristics. Unsupervised domain adaptation (UDA) is a promising solution to tackle this problem. In this work, we present a novel UDA method, named dual adaptation-guiding network (DAG-Net), which incorporates two highly effective and complementary structural-oriented guidance in training to collaboratively adapt a segmentation model from a labelled source domain to an unlabeled target domain. Specifically, our DAG-Net consists of two core modules: 1) Fourier-based contrastive style augmentation (FCSA) which implicitly guides the segmentation network to focus on learning modality-insensitive and structural-relevant features, and 2) residual space alignment (RSA) which provides explicit guidance to enhance the geometric continuity of the prediction in the target modality based on a 3D prior of inter-slice correlation. We have extensively evaluated our method with cardiac substructure and abdominal multi-organ segmentation for bidirectional cross-modality adaptation between MRI and CT images. Experimental results on two different tasks demonstrate that our DAG-Net greatly outperforms the state-of-the-art UDA approaches for 3D medical image segmentation on unlabeled target images.

Due to the openness nature of wireless medium, security issues have increasingly become a bottleneck that restricts the development of ultra-reliable and low-latency communications (uRLLCs). Physical layer security (PLS) technique has been proposed to fulfill the security and confidentiality of information transmission by exploiting the characteristics of the wireless channel, which caters to the features of uRLLC. Furthermore, PLS also shows great practicality in artificial intelligence field, especially in wireless intelligent networks. However, the previous works on the study of PLS ignored the significance of mobility and limited packet length constraint required by uRLLC for satisfying low latency, in this paper, we investigate the impact of mobility on the secrecy performance of uRLLC by using the Random WayPoint (RWP) model and the Random Direction (RD) model. Specifically, with the tools of stochastic geometry, to observe the impact of key system parameters on the secrecy performance, we establish the closed-form expression of connection outage probability, secrecy outage probability, and decoding error probability-based secrecy transmission capacity (DEP-STC). Furthermore, we derive the condition that achieves a positive DEP-STC under two moving models, which can offer the network designer some greatly significant insights into achieving perfect secrecy. Simulations validate our derived theoretical results, and indicate that RWP moving receiver can obtain a higher security level than RD moving one, while RWP eavesdropper can lead to a lower security.

Nodes in wireless sensor networks (WSNs) are usually deployed in an unattended even hostile environment. What is worse, these nodes are equipped with limited battery, storage, computation, and communication resources. Therefore, it is challenging to ensure the security of a WSN without decreasing its network performance. Data aggregation (DA) combined with a security mechanism can provide a good scheme for solving the aforementioned problems. This article presents a comprehensive review of secure DA (SDA) in WSNs, including its security goals together with the existing problems. The traditional network topologies as well as new emerging ones are discussed and compared in order to indicate the application scenes and security levels of different topologies. Meanwhile, the contrastive analyses of security strategies are presented which divides SDA protocols into five categories according to different security mechanisms, security goals, and network topologies. Besides, the discussion points out some open issues which may be the valuable topics of SDA in the future.

Wireless Sensor Networks (WSNs) are increasingly involved in many applications. However, communication overhead and energy efficiency of sensor nodes are the major concerns in WSNs. In addition, the broadcast communication mode of WSNs makes the network vulnerable to privacy disclosure when the sensor nodes are subject to malicious behaviours. Based on the abovementioned issues, we present a Queries Privacy Preserving mechanism for Data Aggregation (QPPDA) which may reduce energy consumption by allowing multiple queries to be aggregated into a single packet and preserve data privacy effectively by employing a privacy homomorphic encryption scheme. The performance evaluations obtained from the theoretical analysis and the experimental simulation show that our mechanism can reduce the communication overhead of the network and protect the private data from being compromised.