A DRL-Empowered Multi-Level Jamming Approach for Secure Semantic Communication

TL;DR

This paper introduces a DRL-based multi-level jamming strategy to secure semantic communication systems, effectively protecting transmitted information from eavesdroppers while maintaining high-quality communication for legitimate users.

Contribution

It proposes a novel multi-level jamming approach combined with DRL for dynamic precoding, enhancing security and communication quality in semantic systems over MIMO channels.

Findings

Achieves comparable security to encryption-based methods.

Improves legitimate user's PSNR by up to 0.6 dB.

Demonstrates effective joint training of SemCom and DRL modules.

Abstract

Semantic communication (SemCom) aims to transmit only task-relevant information, thereby improving communication efficiency but also exposing semantic information to potential eavesdropping. In this paper, we propose a deep reinforcement learning (DRL)-empowered multi-level jamming approach to enhance the security of SemCom systems over MIMO fading wiretap channels. This approach combines semantic layer jamming, achieved by encoding task-irrelevant text, and physical layer jamming, achieved by encoding random Gaussian noise. These two-level jamming signals are superposed with task-relevant semantic information to protect the transmitted semantics from eavesdropping. A deep deterministic policy gradient (DDPG) algorithm is further introduced to dynamically design and optimize the precoding matrices for both task-relevant semantic information and multi-level jamming signals, aiming to enhance the legitimate user's image reconstruction while degrading the eavesdropper's performance. To jointly train the SemCom model and the DDPG agent, we propose an alternating optimization strategy where the two modules are updated iteratively. Experimental results demonstrate that, compared with both the encryption-based (ESCS) and encoded jammer-based (EJ) benchmarks, our method achieves comparable security while improving the legitimate user's peak signal-to-noise ratio (PSNR) by up to approximately 0.6 dB.