Abstract
In this paper, a novel covert semantic communication framework is investigated for image transmission. Within this framework, a server extracts and transmits the semantic information, i.e., the meaning of image data, to a user. An attacker seeks to detect and eavesdrop the semantic transmission to acquire the details of the original image. To secure the semantic communications from such eavesdropping attack, a friendly jammer is deployed to transmit jamming signals so as to interfere the attacker. To evaluate the quality of the received and the eavesdropped semantic information, we introduce a semantic similarity metric called graph-to-nearest-triple (GNT). The privacy level of the system is quantified as the difference between the GNT of the received semantic information at the user and the attacker. The server and the jammer collaboratively manage their transmit power to maximize the privacy level of the semantic communication. To solve this non-convex power management problem, we propose a step-wise dense reward function guided recurrent Q learning algorithm to jointly optimize the transmit power at the server and friendly jammer with no inter-device communication, such that the considered problem is solved in a spectrally, computationally and space compact way. Simulation results show that the proposed method can improve privacy and the semantic transmission quality by up to 17.2% improvement compared to the traditional RL based solutions.