Intelligent reflecting surface backscatter-enabled physical layer security enhancement via deep reinforcement learning

作     者：Ahmed, Manzoor Hussain, Touseef Shahwar, Muhammad Khan, Feroz Sheraz, Muhammad Khan, Wali Ullah Chuah, Teong Chee Lee, It Ee 

作者机构：Artificial Intelligence Industrial Technology Research Institute Hubei Engineering University Xiaogan China Hubei Engineering University Xiaogan China School of Electronic Science and Technology Beijing University of Posts and Telecommunications Beijing China School of Computer Science and Technology Qingdao University Qingdao China Centre for Smart Systems and Automation CoE for Robotics and Sensing Technologies Faculty of Artificial Intelligence and Engineering Multimedia University Persiaran Multimedia Selangor Cyberjaya Malaysia  University of Luxembourg Luxembourg 

出 版 物：《PeerJ Computer Science》 (PeerJ Comput. Sci.)

年 卷 期：2025年第11卷

页      面：e2902-e2902页

核心收录：

基　　金：This work was supported by the Multimedia University Research Fellow Grant (MMUI/ 240021) and the TM Research and Development Grant (RDTC/241149). The Hubei Provincial Department of Education Outstanding Youth Scientific Innovation Team Support Foundation (T201410  T2020017)  the Natural Science Foundation of Xiaogan City (XGKJ2022010095  XGKJ2022010094)  the Science and Technology Research Project of Education Department of Hubei Province (No. Q20222704). The funders had no role in study design  data collection and analysis  decision to publish  or preparation of the manuscript 

主　　题：Backscattering 

摘      要：This article introduces a novel strategy for wireless communication security utilizing intelligent reflecting surfaces (IRS). The IRS is strategically deployed to mitigate jamming attacks and eavesdropper threats while improving signal reception for legitimate users (LUs) by redirecting jamming signals toward desired communication signals leveraging physical layer security (PLS). By integrating the IRS into the backscatter communication system, we enhance the overall secrecy rate of LU, by dynamically adjusting IRS reflection coefficients and active beamforming at the base station (BS). A design problem is formulated to jointly optimize IRS reflecting beamforming and BS active beamforming, considering time-varying channel conditions and desired secrecy rate requirements. We propose a novel approach based on deep reinforcement learning (DRL) named Deep-PLS. This approach aims to determine an optimal beamforming policy capable of thwarting eavesdroppers in evolving environmental conditions. Extensive simulation studies validate the efficacy of our proposed strategy, demonstrating superior performance compared to traditional IRS approaches, IRS backscattering-based antieavesdropping methods, and other benchmark strategies in terms of secrecy performance. © 2025 Ahmed et al.