Deep Learning for Secure Transmission in Reconfigurable Intelligent Surface-Assisted Communications

This paper investigates the secure transmission for reconfigurable intelligent surface (RlS)-assisted wireless communication systems. In the studied model, one user connects to the access point via a RIS while an eavesdropper eavesdrops on the signal sent from the user to the access point. Therefore, it is necessary to design an appropriate RIS reflection vector to solve the eavesdropping problem. This problem is formulated as an optimization problem whose goal is to maximize the secure energy efficiency which is defined as the ratio of the secure rate to the total energy consumption of the system via jointly optimizing the RIS reflection reflector as well as the number of RIS elements, which results in a non-convex optimization problem that is intractable to solve by traditional methods. To tackle this issue, a new algorithm by leveraging the advance of the established deep learning (DL) technique is proposed so as to find the optimal RIS reflection vector and determine the optimal number of RIS reflection elements. Simulation results show that the proposed method reaches 96% of the optimal secure energy efficiency of the genie-aided algorithm.