Learning-based Power Control for Secure Covert Semantic Communication

Yansheng Liu; Jinbo Wen; Zongyao Zhang; Kun Zhu; Yang Zhang; Jiangtian Nie; Jiawen Kang

Learning-based Power Control for Secure Covert Semantic Communication

Networking and Internet Architecture 2025-07-08 v2

Authors: Yansheng Liu , Jinbo Wen , Zongyao Zhang , Kun Zhu , Yang Zhang , Jiangtian Nie , Jiawen Kang

Abstract

Despite progress in semantic communication (SemCom), research on SemCom security is still in its infancy. To bridge this gap, we propose a general covert SemCom framework for wireless networks, reducing eavesdropping risk. Our approach transmits semantic information covertly, making it difficult for wardens to detect. Given the aim of maximizing covert SemCom performance, we formulate a power control problem in covert SemCom under energy constraints. Furthermore, we propose a learning-based approach based on the soft actor-critic algorithm, optimizing the power of the transmitter and friendly jammer. Numerical results demonstrate that our approach effectively enhances the performance of covert SemCom.

Keywords

semantic communication physical layer security wiretap channel

Cite

@article{arxiv.2407.07475,
  title  = {Learning-based Power Control for Secure Covert Semantic Communication},
  author = {Yansheng Liu and Jinbo Wen and Zongyao Zhang and Kun Zhu and Yang Zhang and Jiangtian Nie and Jiawen Kang},
  journal= {arXiv preprint arXiv:2407.07475},
  year   = {2025}
}

Learning-based Power Control for Secure Covert Semantic Communication

Abstract

Keywords

Cite

Related papers