Nov 2026· Journal of King Saud University: Computer and Information Sciences· Vol 38· 0 citations· 39 references
TL;DR
A robust soft-fusion SAC-Lagrangian algorithm is developed that achieves faster stabilization of the training curve, a higher average secrecy rate, a higher worst-user secrecy rate, and a significantly lower constraint-violation probability than benchmark schemes.
Abstract
Secure communication is essential in UAV-assisted wireless networks, where the broadcast nature of air-to-ground channels makes legitimate transmissions vulnerable to eavesdropping. Physical layer security (PLS) provides an effective means to mitigate this threat, with secrecy rate commonly adopted as the performance metric. However, practical engineering requirements may further require the eavesdropper’s signal-to-interference-plus-noise ratio (SINR) to remain below a prescribed threshold to prevent reliable decoding. The resulting optimization problem is challenging because both the secrecy-rate objective and the eavesdropper-SINR constraint depend on the unknown locations of passive eavesdroppers, while conventional reinforcement learning (RL) cannot explicitly enforce security-related constraints. To address these challenges, we formulate the problem as a constrained Markov decision process and develop a robust soft-fusion SAC-Lagrangian algorithm. The constrained RL component incorporates a long-term discounted eavesdropper-SINR cost into the learning process through a Lagrangian mechanism, enabling secrecy-rate optimization under explicit security requirements. It should be noted that the original per-slot hard SINR constraint is relaxed into a discounted cumulative-cost constraint when the problem is formulated as a CMDP, which is the standard formulation for long-term policy learning. To handle eavesdropper-location uncertainty, the potential eavesdropping region is partitioned into multiple subregions, and parallel reward-critic pairs are used to evaluate the worst-case secrecy performance in each subregion, while a single global cost critic evaluates the softmax-fused constraint cost. Their outputs are then fused to learn a single robust policy that balances secrecy-rate maximization and constraint satisfaction across uncertain eavesdropper locations. Simulation results show that the proposed method achieves faster stabilization of the training curve, a higher average secrecy rate, a higher worst-user secrecy rate, and a significantly lower constraint-violation probability than benchmark schemes.
Unmanned aerial vehicle (UAV)-enabled communications provides a cost-effective option for next-generation wireless networks. Nevertheless, the inherently open characteristics of air-to-ground links leave such communications particularly susceptible to eavesdropping. Motivated by this vulnerability, this paper studies a...
This paper proposes a robust beamforming framework for a full-duplex (FD) integrated secure communication, computation, and energy (ISC2E) network. In the considered network, an FD base station (BS) simultaneously performs downlink wireless power transfer while aggregating uplink over-the-air computation data and recei...
Chang-Jie Hu, Jiashuo Sun, Tuo Wu et al.· IEEE Transactions on Wireles...· 0 citations
This paper investigates the joint optimization of resource allocation and unmanned aerial vehicle (UAV) trajectory in a UAV‐assisted two‐hop status update system, where secure and covert transmission is achieved under the finite blocklength (FBL) regime. A ground source transmits status updates to a destination via a...
Ting Zhang, Man-Gang Xie, Jing Wei et al.· Internet Technology Letters· 0 citations
Numerical results demonstrate that the proposed AN-aided RSMA secure precoding scheme significantly outperforms conventional multiple access schemes in terms of secrecy performance and robustness against the Eve CSI uncertainty.
Meng-Yan Huang, Zi-Wen Wei, Xing-Wang Li et al.· IEEE Transactions on Communi...· 0 citations
This paper investigates an active simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS)-aided secure ISCPT system, and proposes a long short-term memory-enhanced proximal policy optimization (LSTM-PPO) deep reinforcement learning framework that achieves superior convergence performanc...
Fang-Qing Tan, Jin-Hong Zhang, Hong-Bin Chen et al.· IEEE Transactions on Green C...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.