Real-Time and Security-Aware Precoding in RIS-Empowered Multi-User Wireless Networks

TL;DR

This work addresses secrecy-rate optimization in RIS-enabled multi-user wireless networks under CSI uncertainties and nonconvex constraints. It presents an AO-based solution for a relaxed problem and derives KKT-based closed-form beamforming and phase-shift updates, then unfolds these updates into a deep neural network (DUNet) to enable real-time inference. DUNet achieves near-AO performance (approximately 99.6% of AO secrecy rate) with a substantial speedup (about 25.6x), making secure RIS precoding viable for 6G-scale systems. The approach combines SDR, Bernstein-type inequalities, and deep unfolding to deliver secure, low-latency precoding suitable for practical deployments.

Abstract

In this letter, we propose a deep-unfolding-based framework (DUNet) to maximize the secrecy rate in reconfigurable intelligent surface (RIS) empowered multi-user wireless networks. To tailor DUNet, first we relax the problem, decouple it into beamforming and phase shift subproblems, and propose an alternative optimization (AO) based solution for the relaxed problem. Second, we apply Karush-Kuhn-Tucker (KKT) conditions to obtain a closed-form solutions for the beamforming and the phase shift. Using deep-unfolding mechanism, we transform the closed-form solutions into a deep learning model (i.e., DUNet) that achieves a comparable performance to that of AO in terms of accuracy and about 25.6 times faster.

Figures (6)

• Figure 1: RIS-empowered multiuser network.
• Figure 2: Structure of the proposed DUNet.
• Figure 3: Secrecy rate versus $P_B$.
• Figure 4: Achievable secrecy rate versus RIS elements.
• Figure 5: Secrecy rate versus rate threshold $\varepsilon_k$.