This paper investigates a downlink covert communication system based on rate-splitting multiple access (RSMA), assisted by a reconfigurable intelligent surface (RIS) and a jammer. This scheme treats every user in the system as requiring covert transmission and splits each user's message stream into common and private parts to meet the covert communication demands in multi-user scenarios. We derive a closed-form approximate expression for the average minimum detection error probability (AMDEP). Through extensive simulations, the correctness of the analysis and the covertness of the communication system are validated.

A comprehensive performance analysis is conducted for pinching-antenna systems (PASS) under non-orthogonal multiple access (NOMA) transmission. Specifically, a downlink scenario is investigated, in which a pinching antenna is dynamically activated along a dielectric waveguide to serve two users located in separate rooms. The wireless links between the pinching antenna and the users are modeled using a line-of-sight (LoS) and non- line-of-sight (NLoS) propagation conditions, respectively. Closed- form expressions are derived for the outage probabilities (OPs) of the two users. Furthermore, asymptotic analyses in the high signal-to-noise ratio (SNR) regime are conducted to reveal the achievable diversity orders. Numerical simulations validate the accuracy of the theoretical analysis and demonstrate that: 1) Compared with conventional antenna systems (CASS), the OP of the LoS user in PASS is significantly reduced in the middle SNR regime and approaches zero as SNR increases; 2) Since the diversity orders of the NLoS user in CASS and PASS are the same, the movement of the pinching antenna has no significant effect on the OP of the NLoS user.

With the advent of sixth-generation (6G) technologies and growing communication demands, Low Earth Orbit (LEO) satellite networks have become essential in modern communications. However, due to the dynamic topology and complex network state of LEO environments, existing routing methods often fail to make effective decisions, limiting transmission performance. This paper proposes a LEO satellite routing method based on incremental evolutionary graph reinforcement learning (IEGRL). To address network state perception challenges, we introduce a topological learning model using deep graph attention (DGA), which captures complex inter-satellite connectivity and resource states. Additionally, by integrating incremental evolution strategies (IES) into deep reinforcement learning (DRL), we replace sequential interactive proximal policy optimization (PPO) with global parallel ES, achieving efficient routing convergence in the highly dynamic LEO environment. Experimental results demonstrate that our IEGRL approach enhances LEO network load balancing by reducing end-to-end (E2E) network latency, decreasing packet loss, and improving throughput compared with the benchmark approaches.

The computational power required for training deep learning models has been skyrocketing in the past decade as they scale with big data, and has become a very expensive and scarce resource. Therefore, distributed training, which can leverage distributed available computational power, is vital for efficient large-scale model training. However, most previous distributed training frameworks like DDP and DeepSpeed are primarily designed for co-located clusters under homogeneous computing and communication conditions, and hence cannot account for geo-distributed clusters with both computing and communication heterogeneity. To address this challenge, we develop a new data parallel based distributed training framework called Co-Adaptive Data Parallelism (C-ADP). First, we consider a data owner and parameter server that distributes data to and coordinates the collaborative learning across all the computing devices. We employ local training and delayed parameter synchronization to reduce communication costs. Second, we formulate a data parallel scheduling optimization problem to minimize the training time by optimizing data distribution. Third, we devise an efficient algorithm to solve this scheduling problem, and formally prove that the obtained solution is optimal in the asymptotic sense. Experiments on the ImageNet100 dataset demonstrate that C-ADP achieves fast convergence in heterogeneous distributed training environments. Compared to Distributed Data Parallel (DDP) and DeepSpeed, C-ADP achieves 21.6 times and 26.3 times improvements in FLOPS, respectively, and a reduction in training time of about 72% and 47%, respectively.

Low Earth orbit (LEO) satellite networks are an important component of future 6G. However, due to the unique characteristics of the space environment—such as the complexity in modeling network states and the rapid dynamics of the network topology—existing routing methods often struggle to make appropriate routing decisions in the LEO satellite network context, which significantly limits network transmission performance. In this paper, we propose a dynamic satellite routing method based on deep graph attention and incremental evolution strategy (DGA-IES). Firstly, to address the challenge of accurately perceiving satellite network information, we introduce a topological perception learning model based on deep graph attention. By combining an enhanced message passing process with a self-attention mechanism, this model effectively captures complex features of the LEO network state, including inter-satellite connectivity relationships, as well as the resource states of satellites and links. Secondly, to tackle the problem of inefficient routing re-convergence in rapidly changing topologies, this paper integrates evolution strategies (ES) into deep reinforcement learning (DRL) approaches. We use the global parallel processing capabilities of ES to replace the sequential interactive proximal policy optimization (PPO) strategy in existing DRL. Moreover, we design an incremental evolutionary process based on satellite motion patterns, facilitating efficient routing convergence in highly dynamic satellite environments. Experimental results demonstrate that our DGA-IES approach enhances LEO network load balancing by reducing end-to-end (E2E) network latency by 10.3% 58.1%, decreasing packet loss by 3.8% 20.0%, and improving throughput by 11.1% 57.0% compared with the benchmark approaches.

Satellite edge computing (SEC) extends the capabilities of edge computing technology to satellite networks, facilitating rapid local processing of global task requirements. Deep reinforcement learning (DRL) has emerged as a promising approach for SEC scenarios due to its inherent dynamic adaptability, complex state modeling capability, and long-term optimization potential. However, existing DRL-based computing offloading techniques continue to encounter challenges including low sample efficiency, poor decision quality, and insufficient long-term stability, which constrain their performance in real satellite network environments. To address these challenges, this study proposes a diffusion and DRL-based approach for computation offloading in SEC networks called the generative artificial intelligence-DRL (GenAI-DRL). First, by implementing the cooperative computing model of the multi-SEC, this study comprehensively considers the heterogeneous computing and communication capabilities of satellite nodes, diversity of task types, and dynamic distribution of resources in an offloading strategy, thereby ensuring long-term system sustainability under dynamic resource constraints and provides a solid foundation for computation offloading in satellite networks with time-varying resource. Second, we integrate generative diffusion modeling (GDM) into the DRL framework to enhance policy generation by producing contextually relevant and high-quality action samples. This not only reduces the dependence on large-scale training data but also improves decision precision and generalization in complex, high-dimensional environments. Finally, a Lyapunov optimization framework is introduced to transform the offloading problem into an online per-slot optimization process, thereby ensuring the long-term stability of the SEC system under dynamic and unpredictable task arrivals and environmental conditions. The experimental results demonstrate that the method proposed offers significant advantages over the existing approaches in reducing task latency and enhancing system stability.

Recent researches have shown that non-sequential tasks based on deep neural networks (DNN), such as image classification and object detection, are vulnerable to backdoor attacks, leading to incorrect model predictions. As a crucial task in computer vision, Scene Text Recognition (STR) is widely used in IoT fields such as intelligent transportation systems and intelligent surveillance. Given its importance, ensuring the security and accuracy of STR models is critical. However, there are currently no studies on STR backdoor attacks. In this paper, we make the first attempt to validate backdoor threats on STR models by using a Patch-Based Attack method. Our experimental results confirm that STR models can be successfully compromised with attack success rate (ASR) of over 80% on most datasets. However, we also reveal a critical flaw: the Patch-Based attack lacks robustness due to the specific preprocessing in STR models (such as resizing and TPS rectification), which distort or eliminate the backdoor triggers. To address this, we further propose BadSTR, a novel backdoor attack method that uses semantic text sequences as triggers. Extensive experiments on eight benchmark datasets show that our proposed BadSTR achieves ASR of over 90% for most model-dataset combinations with significantly improved robustness.

Recent studies have demonstrated that malicious adversaries are capable of fingerprinting Internet of Things (IoT) devices in a smart home and further causing privacy breaches. However, many existing anti-fingerprinting schemes, either by traffic padding or traffic mutation, are less effective in defending against state-of-the-art fingerprinting methods. To meet this gap, we in this paper propose the HomeSentinel, an intelligent anti-fingerprinting scheme to counter IoT traffic fingerprinting in smart homes. Specifically, we first design a LightGBM-based IoT traffic extraction model to accurately distinguish IoT traffic from raw network traffic in a smart home without user operations. Second, we develop a dummy IoT traffic generation model to produce dummy IoT traffic in desired spatial-temporal patterns. Third, an IoT traffic mixing strategy is crafted to heuristically merge dummy IoT traffic with real IoT traffic in desired spatial-temporal patterns. Extensive experiments on three real-world datasets (i.e., two public and one custom) demonstrate that our proposed HomeSentinel scheme can effectively defend against state-of-the-art IoT traffic fingerprinting methods, and outperforms existing IoT traffic anti-fingerprinting schemes. Further, real-world experiments are conducted on a self-built testbed show that, reasonably low communication delays can be caused when implementing the HomeSentinel in smart homes.

Mobile edge computing (MEC) is a key enabling technology for the sixth-generation (6G) wireless networks. In this paper, we apply covert communications to MEC to prevent information leakage, where two candidate technologies of 6G, reconfigurable intelligent surface (RIS) and non-orthogonal multiple access (NOMA), are adopted. Specifically, a legitimate transmitter sends messages to a pair of legitimate receivers, while a warden aims to detect whether the legitimate transmission exists. We can hide the existence of the stronger-signal receiver's transmission from the warden by exploiting the nature of NOMA, and we use a jammer to further hide this existence. We first analyze the performance for the case of fixed power allocation between the legitimate transmitters and the jammer. The closed-form expressions for the minimum detection error probability and ergodic public/covert rates are derived. Then, we design a reinforcement learning (RL)-based power-allocation optimization algorithm that maximizes the sum rate while ensuring covertness, by optimizing the power allocation between the transmitters and the jammer. Simulation results validate the correctness of our analysis and demonstrate the covertness of the proposed scheme. Furthermore, the performance of the RL-based algorithm is significantly better than that of the baseline scheme, which reflects the effectiveness of our proposed algorithm.

Image transmission over wireless communications can be used in a variety of applications, such as smart cities, surveillance systems, and Metaverse construction. In this paper, we propose a task-oriented semantic information transmission (SIT) framework with rate-splitting multiple access (RSMA) for image transmission. As such, only the semantic information of interest is transmitted to each user, and RSMA is adopted to improve transmission efficiency. We also design the quality of experience (QoE) for the framework as a performance metric, which can be used for transmission-parameter optimization. Specifically, we first optimize power allocation with the top-Ncommon message selection strategy. To further improve system performance, we jointly optimize power allocation and common message selection. Simulation results show that the proposed task-oriented SIT framework with RSMA outperforms the space-division multiple access (SDMA)-based benchmark, which reflects the effectiveness of the proposed framework. Furthermore, the results show that optimizing power allocation can improve performance significantly as compared with fixing power allocation, and the joint optimization of power allocation and common message selection has an obvious performance gain over optimizing only power allocation, which demonstrates the effectiveness of the designed optimization algorithms.

In this paper, we propose an interest-based semantic information transmission framework with rate splitting multiple access (RSMA), to reduce the amount of transmitted data, thereby reducing the burden of data transmission and data processing. In the framework, only the semantic information of interest is transmitted to each user. In the process of semantic information transmission, RSMA is adopted to improve transmission efficiency. In particular, we adopt maximum ratio transmission and zero-forcing for the precoding of the common and private streams, respectively. We also design the quality of experience (QoE) for the system as a performance metric. Experimental results demonstrate the effectiveness of the proposed framework as compared with the benchmark.

In this paper, we apply covert communications to reconfigurable intelligent surface (RIS)-assisted non-orthogonal multiple access (NOMA) networks, where a legitimate transmitter sends messages to a pair of legitimate users while a warden aims to detect whether the legitimate transmission exists. We can hide the existence of the strong user's transmission from a warden by exploiting the nature of NOMA, i.e., allocating less power to the strong user, and we use a jammer to further hide that existence. Correspondingly, we analyze the system performance and obtain the closed-form expression for the minimum detection error probability. Simulation results validate the correctness of our analysis and demonstrate the covertness of the proposed scheme.

The semantic communication system enables wireless devices to communicate effectively with the semantic meaning of the data. Wireless powered Internet of Things (IoT) that adopts the semantic communication system relies on harvested energy to transmit semantic information. However, the issue of energy constraint in the semantic communication system is not well studied. In this paper, we propose a semantic-based energy valuation and take an economic approach to solve the energy allocation problem as an incentive mechanism design. In our model, IoT devices (bidders) place their bids for the energy and power transmitter (auctioneer) decides the winner and payment by using deep learning based optimal auction. Results show that the revenue of wireless power transmitter is maximized while satisfying Individual Rationality (IR) and Incentive Compatibility (IC).

Unmanned aerial vehicles (UAVs) have attracted a lot of research attention in serving as aerial base stations (BSs). To protect the data privacy without being detected by a warden, we investigate a jammer-aided UAV covert communication system, aiming to maximize the user's covert rate with optimized transmit and jamming power. By considering the general composite fading and shadowing channel models, we derive the closed-form expressions for detection error probability and covert rate. The covert rate maximization problem is formulated as a Nash bargaining game, and the Nash bargaining solution (NBS) is introduced. To solve the NBS, we propose a particle swarm optimization-based power allocation algorithm. The numerical results are presented to verify the theoretical analysis.

Current strategies for joint radar-communication (JRC) rely on prior knowledge of the communication and radar systems within the vehicle network. In this paper, we propose a framework for intelligent vehicles to conduct JRC, with minimal prior knowledge, in an environment where surrounding vehicles execute radar detection periodically, which is typical in contemporary protocols. We introduce a metric on the usefulness of data to help the vehicle decide what, and to whom, data should be transmitted. The problem framework is cast as a Markov Decision Process (MDP). We show that deep reinforcement learning results in superior performance compared to nonlearning algorithms. In addition, experimental results show that the trained deep reinforcement learning agents are robust to changes in the number of vehicles in the environment.

Unmanned aerial vehicles (UAVs) have attracted a lot of research attention because of their high mobility and low cost in serving as temporary aerial base stations (BSs) and providing high data rates for next-generation communication networks. To protect user privacy while avoiding detection by a warden, we investigate a jammer-aided UAV covert communication system, which aims to maximize the user’s covert rate with optimized transmit and jamming power. The UAV is equipped with multi-antennas to serve multi-users simultaneously and enhance the Quality of Service. By considering the general composite fading and shadowing channel models, we derive the exact probability density (PDF) and cumulative distribution functions (CDF) of the signal-to-interference-plus-noise ratio (SINR). The obtained PDF and CDF are used to derive the closed-form expressions for detection error probability and covert rate. Furthermore, the covert rate maximization problem is formulated as a Nash bargaining game, and the Nash bargaining solution (NBS) is introduced to investigate the negotiation among users. To solve the NBS, we propose two algorithms, i.e., particle swarm optimization-based and joint two-stage power allocation algorithms, to achieve covertness and high data rates under the warden’s optimal detection threshold. All formulated problems are proven to be convex, and the complexity is analyzed. The numerical results are presented to verify the theoretical performance analysis and show the effectiveness and success of achieving the covert communication of our algorithms.

In this paper, non-orthogonal multiple access (NOMA) networks assisted by multiple intelligent reflecting surfaces (IRSs) with discrete phase shifts are investigated, in which each user device (UD) is served by an IRS to improve the quality of the received signal. Two scenarios are considered according to whether there is a direct link between the base station (BS) and each UD, and the outage performance is analyzed for each of them. Specifically, the asymptotic expressions for the upper and lower bounds of the outage probability in the high signal-to-noise ratio (SNR) regime are derived. Following that, the diversity order is obtained. It is shown that the use of discrete phase shifts does not degrade diversity order. More importantly, simulation results reveal that a 3-bit resolution for discrete phase shifts is sufficient to achieve near-optimal outage performance. Simulation results also imply the superiority of IRSs over full-duplex decode-and-forward relays.

Intelligent reflecting surfaces (IRSs) are envisioned to provide reconfigurable wireless environments for future communication networks. In this paper, both downlink and uplink IRS-aided non-orthogonal multiple access (NOMA) and orthogonal multiple access (OMA) networks are studied, in which an IRS is deployed to enhance the coverage by assisting a cell-edge user device (UD) to communicate with the base station (BS). To characterize system performance, new channel statistics of the BS-IRS-UD link with Nakagami-$m$fading are investigated. For each scenario, the closed-form expressions for the outage probability and ergodic rate are derived. To gain further insight, the diversity order and high signal-to-noise ratio (SNR) slope for each scenario are obtained according to asymptotic approximations in the high-SNR regime. It is demonstrated that the diversity order is affected by the number of IRS reflecting elements and Nakagami fading parameters, but the high-SNR slope is not related to these parameters. Simulation results validate our analysis and reveal the superiority of the IRS over the full-duplex decode-and-forward relay.

In this paper, a downlink non-orthogonal multiple access (NOMA) system is studied, in which an intelligent reflecting surface (IRS) is deployed to enhance the coverage by assisting a cell-edge user device (UD) to communicate with the base station (BS). To characterize system performance, new channel statistics for the BS-IRS-UD link with Nakagami-m fading are investigated. Based on the new channel statistics, the closed-form expression for the outage probability is derived. To gain further insight into the problem, the diversity order is obtained according to the asymptotic approximation in the high signal-to-noise ratio (SNR) regime. It is demonstrated that the diversity order is affected by the number of IRS elements and Nakagami fading parameters. Simulation results validate our analysis and reveal the superiority of the IRS over the full-duplex decode-and-forward relay in the high-SNR regime.

A joint user clustering and subcarrier allocation scheme for downlink non-orthogonal multiple access (NOMA) systems is examined in this paper. We propose the scheme for downlink NOMA systems which maximizes the achievable diversity order. The closed-form expression of the outage probability of the worst-performance user in the worst case is derived and validated by simulations. Numerical results show that the proposed scheme can achieve the same diversity order as the exhaustive searching scheme.