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

2025-08-10

AI Summary

This paper addresses the challenge of simultaneously ensuring user privacy and semantic transmission quality in non-cooperative semantic communication scenarios. We propose a covert semantic communication framework that jointly optimizes multi-slot semantic information selection and dynamic power allocation—without requiring explicit coordination between the server and friendly jammers. A novel non-cooperative jamming mechanism is designed, and a reinforcement learning algorithm based on Twin-Delayed Deep Deterministic Policy Gradient (TD3) with prioritized experience replay is developed; dual Q-networks are incorporated to mitigate value estimation bias and prevent policy convergence to local optima. Experimental results demonstrate that the proposed method improves privacy protection performance and semantic transmission quality by 77.8% and 14.3%, respectively, over conventional approaches, significantly enhancing the robustness and effectiveness of semantic-level covert transmission.

Technology Category

• Machine Learning: Privacy
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Prevent eavesdropping on semantic image data transmission
• Optimize transmit power and semantic info without jammer coordination
• Enhance privacy and transmission quality using novel RL algorithm

Innovation

• Covert semantic communication with friendly jammer
• Prioritised sampling assisted reinforcement learning
• Joint optimization of transmission and power