Deep Learning Based Joint Beamforming Design in IRS-Assisted Secure Communications

Chi Zhang, Yiliang Liu, Hsiao Hwa Chen

研究成果: Article同行評審


In this paper, physical layer security (PLS) in an intelligent reflecting surface (IRS) assisted multiple-input multiple-output multiple-antenna eavesdropper (MIMOME) system is studied. In particular, we consider a practical scenario without instantaneous channel state information (CSI) of the eavesdropper and assume that the eavesdropping channel is a Rayleigh channel. To deal with the complexity of currently available IRS-assisted PLS schemes, we propose a low-complexity deep learning (DL) based approach to design transmitter beamforming and IRS jointly, where precoding vector and phase shift matrix are used to minimize the secrecy outage probability. Simulation results demonstrate that the proposed DL-based approach can achieve a similar performance of that with conventional alternating optimization (AO) algorithms with a significantly low computational complexity.

頁(從 - 到)16861-16865
期刊IEEE Transactions on Vehicular Technology
出版狀態Published - 2023 12月 1

All Science Journal Classification (ASJC) codes

  • 汽車工程
  • 航空工程
  • 電腦網路與通信
  • 電氣與電子工程


深入研究「Deep Learning Based Joint Beamforming Design in IRS-Assisted Secure Communications」主題。共同形成了獨特的指紋。