The cognitive satellite-terrestrial network (CSTN) has emerged as a transformative architecture for enabling ubiquitous global connectivity, yet its broadcast nature and heterogeneous service demands pose critical security challenges against increasingly sophisticated wiretap threats. This paper proposes a novel reconfigurable intelligent surface (RIS)-assisted secure sparse code multiple access (SCMA) framework in CSTN, which aims to maximize the achievable secrecy rate by jointly optimizing the transmit beamforming, RIS reflection matrix, and SCMA codebook configuration while satisfying power constraints at the satellite and base station and meeting the quality-of-service demands of legitimate users. Specifically, a realistic RIS model incorporating coupled phase-amplitude constraints is considered for practical deployment scenarios. To solve the above non-convex optimization problem in dynamic environments, an intelligent decision-making mechanism based on a modified multi-agent two-delay deep deterministic (MMTD3) algorithm is developed to effectively decouple continuous beam control and discrete codebook selection, and provide a new paradigm for AI-driven cross-domain security optimization in CSTN. Simulation experiments demonstrate that the proposed framework outperforms existing benchmarks in key metrics including convergence, reward values, and secrecy rate, highlighting the framework’s potential for supporting ubiquitous security and massive heterogeneous service demands in CSTN.

In recent years, physical layer security (PLS) techniques have been paid considerable attention due to its high-security level and strong compatibility. However, the request of the superior legitimate channel is the Achilles’ Heel of PLS. A significant challenge exists in ensuring information confidentiality when the eavesdropper locates at user’s direction in the multi-antenna system. To overcome this limitation, we propose a novel framework to achieve secure communication via distributed split single sideband (SSB) time modulated array (TMA). By strategically dividing the I/Q paths of the transmitted signals into geographically separated subarrays, we establish the non-aliasing zone to achieve error-free communication for legitimate user (LU), while the eavesdropper positioned in the aliasing zone receives irrecoverably disturbed waveform. To assess performance, we adopt the encoder-decoder-based deep neural network to optimize the time-switching sequence, ensuring the subarrays’ spatial radiation areas overlap exclusively at the LU. A specialized loss function is formulated to enhance the interference-to-signal ratio by increasing the −1stto the +1stharmonic power ratio in non-LU regions. Furthermore, the joint optimization improves security by focusing energy on the LU while generating interference in non-LU areas. The bit error rate (BER) is used as the metric, and the simulation results validate the effectiveness of the proposed method, ensuring reliable transmission and increasing Eve’s BER to approximately 0.5, thereby compromising her ability to intercept the communication.

As a key component of the space-air-ground integrated network (SAGIN), low Earth orbit (LEO) satellites aim to provide global coverage and reliable services under high-speed mobile conditions, which are critically challenged by severe Doppler effect and inherent broadcast security threats. To address these issues, this paper investigates a multi-reconfigurable intelligent surface (RIS)-assisted orthogonal time frequency space (OTFS) downlink transmission system, where a LEO satellite serves multiple information receivers and potential eavesdroppers acting as energy receivers via simultaneous wireless information and power transfer (SWIPT). By jointly optimizing multi-dimensional resource variables, such as transmit beamforming and RIS reflection coefficients of the spatial domain, and the symbol scheduling matrix of the time-frequency domain, this paper aims to maximize the sum secrecy rate while satisfying constraints on satellite transmit power, the legitimate users’ quality of service, and energy-harvesting requirements. Given the high-dimensional, non-convex, and NP-hard nature of this problem, we develop an enhanced actor-critic deep reinforcement learning (DRL) framework. The core innovation lies in designing an episodic return-prioritized experience selection mechanism with online mixing, which significantly improves the sampling efficiency and policy stability by intelligently selecting training data. Simulation results demonstrate that the proposed approach outperforms existing schemes in achieving a higher sum secrecy rate, providing a practical and highly efficient resource scheduling solution for building secure and reliable next-generation SAGIN.

Massive multiple-input multiple-output (MIMO) systems with one-bit analog-to-digital converters (ADCs) face a severe trade-off between hardware efficiency and channel estimation accuracy. While generative adversarial networks (GANs) show promise for this challenge, their deployment is hindered by training instability and mode collapse. To address these issues, we propose ReRpGAN, a novel adversarial learning framework that integrates a regularized relativistic pairing GAN loss and anL1loss within a deep residual network. This architecture effectively stabilizes the training process and prevents mode collapse, enabling precise channel reconstruction from severely quantized signals. Extensive experiments on a realistic ray-tracing channel dataset validate our theoretical claims. Key findings demonstrate that ReRpGAN consistently outperforms conventional GAN-based and deep learning estimators, particularly in challenging scenarios with low signal-to-noise ratios and limited pilot overhead. Furthermore, unlike existing methods that suffer from divergence, ReRpGAN exhibits superior scalability, delivering improved estimation accuracy as the number of base station antennas increases. This work sets a new benchmark for robust, data-driven channel estimation in next-generation wireless systems.

Achieving real-time processing in integrated sensing and communication (ISAC) systems presents significant challenges due to the high computational burden of conventional optimization methods, particularly within intelligent transportation networks (ITN). This paper addresses these challenges by proposing lightweight supervised and unsupervised deep learning (DL) algorithms, respectively for quasi-static and dynamic environments, aiming to improve the secrecy energy efficiency (SEE) of ITN under the constraints of the Cram´er-Rao bound (CRB) for direction-of-arrival (DOA) estimation and the transmission rate of each user. By jointly optimizing power allocation and reconfigurable intelligent surface (RIS) phase shifts, the framework ensures robust physical layer security (PLS) alongside communication efficiency, aligning with defense-in-depth strategies for securing next-generation ITN. For quasi-static environments, a supervised deep neural network (DNN) algorithm leverages offline codebook-generated labels to achieve near-optimal channel state information (CSI) mapping, explicitly minimizing signal leakage to eavesdroppers. In dynamic scenarios, an unsupervised channel attention mechanism-based residual network (CAM-ResNet) eliminates labeling overhead through direct physics-informed SEE optimization with adaptive constraint enforcement, enabling real-time adaptation to rapidly varying channels and evolving security threats. Simulation results demonstrate that both algorithms achieve comparable SEE performance with the zero-forcing (ZF) method, while significantly reducing computational complexity, with the CAM-ResNet demonstrating superior resilience to dynamic security threats. This work contributes to advancing secure and efficient ISAC solutions, reinforcing multi-layered defense mechanisms critical for future ITN.

Satellite communications (SatCom) face fundamental security challenges due to their inherent broadcast nature. To address this, we exploit beyond-diagonal reconfigurable intelligent surface (BD-RIS) to unleash its full-scattering matrix control for enhanced secure beamforming flexibility in SatCom with rate-splitting multiple access (RSMA), where the satellite attempts to convey private signals to legitimate users with blocked direct downlinks and multiple eavesdroppers. To maximize the worst-case secrecy rate among legitimate users, a max-min fairness (MMF) problem is formulated with imperfect wiretap channel state information (CSI) via joint precoding, RIS configuration, and rate splitting optimization. By using the block coordinate descent (BCD) method, these optimization variables are decoupled with different subproblems and solved by the penalty dual decomposition (PDD) method iteratively. Furthermore, we develop a computationally efficient suboptimal solution that employs diagonal RIS (D-RIS) with reduced hardware and computational complexity, where alternating optimization (AO) and successive convex approximation (SCA) methods are employed to solve the non-convex problem. Simulation results demonstrate that our proposed BD-RIS-RSMA scheme achieves significant performance improvements compared to baseline schemes, while the suboptimal diagonal RIS scheme offers a favorable performance-complexity tradeoff.

In the context of future 6G networks, reconfigurable intelligent surfaces (RIS) and non-orthogonal multiple access (NOMA) are emerging as pivotal technologies for enhancing signal quality and eliminating coverage blind spots. This paper addresses the issue of secure and resilient transmission in RISassisted NOMA systems. Specifically, the base station transmits private signals to multiple legitimate users while dealing with the threat of potential eavesdropping. To model this challenge, we optimize the beamforming vectors and the RIS phase-shift matrix to maximize the sum secrecy rate while satisfying the user quality of service (QoS) requirements and the power constraints of the base station. Since the problem involves high-dimensional variables and non-convex objective functions, it is difficult to be solved by traditional optimization methods. Therefore, the twin delayed deep deterministic policy gradient algorithm (TD3) based on deep reinforcement learning (DRL) is proposed in this paper to effectively address the complexity of the original problem. Numerical results show that the proposed scheme exhibits satisfactory performance in improving communication security, transmission efficiency, and resistance to channel errors.

Phased array (PA) has received considerable attention as a representative multiantenna technique due to its inherent advantages of superior directionality, spatial multiplexing capabilities, and robust anti-jamming characteristics. However, PA suffers from relatively high hardware complexity and power consumption. As a low-complexity array technology with excellent beamforming capability, time modulated array (TMA) has attracted much attention in recent years. In this article, we exploit a TMA for enhancing the Age of Information (AoI) of covert communication. Specifically, we first propose the transmitter structures and the corresponding beamforming methods for the TMA scheme and the PA scheme as a benchmark. Subsequently, the closed-form expressions of the Kullback-Leibler (KL) divergence is derived to serve as the quantitative measure of communication covertness under both schemes, based on which the average covert AoI (CAoI) is derived to jointly characterize the covertness and timeliness performance. Then, to minimize the average CAoI, the optimization problems of the block-length and beamforming parameters for both the TMA and PA schemes are formulated and solved. Finally, the numerical results are provided to show that the proposed TMA scheme surpasses the PA scheme in terms of both the convergence rate and the average CAoI.

In this article, we investigate covert millimeter-wave (mmWave) communications with finite blocklength, where a multiantenna transmitter sends covert messages to a legitimate receiver in the presence of spatially random wardens. Both the phase array (PA) and linear frequency diverse array (LFDA) beamforming schemes, which are designed to maximize the antenna gain from the transmitter to the legitimate receiver, are investigated to improve the covert communication performance. First, the novel expressions of covert communication constraint and average effective covert throughput (AECT) are derived for both beamforming schemes. Then, taking into account the constraint of maximal available blocklength, the optimal transmit power and blocklength are determined for maximizing the AECT. Typically, comparing to the benchmark with fixed blocklength, the enhancement of AECT by utilizing the optimized blocklength enlarges as the density of wardens increases. In addition, it is observed that increasing the maximal available blocklength cannot always improve the maximum AECT due to the tradeoff between the transmit power and blocklength. Furthermore, it is shown that the maximum AECT varies for different directions of the legitimate receiver under both the beamforming schemes, and the transmitter can adaptively choose the PA or LFDA beamforming scheme to improve the covertness performance against spatially random wardens.

This paper investigates the covert millimeter wave (mmWave) communication in the finite block-length regime, where spatially random wardens attempt to determine the presence of transmission. First, we derive a novel expression of covertness constraint by using the tools of stochastic geometry, based on which the expression of average effective covert throughput (AECT) is also presented. Then, considering the constraint of maximal available block-length, the optimization problem for maximizing the AECT is formulated, and the optimal transmit power and block-length are analytically determined. Our results show the superiority of our optimization in terms of AECT in contrast to the fixed block-length case, and the improvement is more significant when the density of wardens becomes large. Furthermore, the performance of covert mmWave communication can indeed be improved via increasing the number of antennas even there exist random distributed wardens.