Optimization of Private Semantic Communication Performance: An Uncooperative Covert Communication Method

TL;DR

This paper introduces a novel covert semantic communication framework that employs a friendly jammer and a deep reinforcement learning algorithm to optimize privacy and transmission quality without direct communication between server and jammer.

Contribution

It proposes a prioritised sampling twin delayed deep deterministic policy gradient algorithm for joint optimization of semantic data and power, enhancing privacy and quality in covert communication.

Findings

Privacy and transmission quality improved by up to 77.8% and 14.3%.

The proposed method outperforms traditional reinforcement learning approaches.

Effective joint optimization without server-jammer communication.

Abstract

In this paper, a novel covert semantic communication framework is investigated. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user over several time slots. An attacker seeks to detect and eavesdrop the semantic transmission to acquire details of the original image. To avoid data meaning being eavesdropped by an attacker, a friendly jammer is deployed to transmit jamming signals to interfere the attacker so as to hide the transmitted semantic information. Meanwhile, the server will strategically select time slots for semantic information transmission. Due to limited energy, the jammer will not communicate with the server and hence the server does not know the transmit power of the jammer. Therefore, the server must jointly optimize the semantic information transmitted at each time slot and the corresponding transmit power to maximize the privacy and the semantic information transmission quality of the user. To solve this problem, we propose a prioritised sampling assisted twin delayed deep deterministic policy gradient algorithm to jointly determine the transmitted semantic information and the transmit power per time slot without the communications between the server and the jammer. Compared to standard reinforcement learning methods, the propose method uses an additional Q network to estimate Q values such that the agent can select the action with a lower Q value from the two Q networks thus avoiding local optimal action selection and estimation bias of Q values. Simulation results show that the proposed algorithm can improve the privacy and the semantic information transmission quality by up to 77.8% and 14.3% compared to the traditional reinforcement learning methods.