Beamforming Design for Physical Security in Movable Antenna-Aided ISAC Systems: A Reinforcement Learning Approach

In this paper, we investigate a secure Integrated Sensing and Communication (ISAC) system aided by Movable Antennas (MAs). Therein, the positions of the MAs can be dynamically adjusted to enhance channel conditions, thereby improving communication security for legitimate users in the presence of adversaries. Additionally, we consider a realistic scenario, where the Base Station (BS) only has imperfect eavesdropper's Channel State Information (CSI). In this context, our objective is to optimize the system secrecy rate by jointly designing the BS's transmit beamforming vector and MA movement. To address the dynamics of the ISAC environments and uncertainties of the imperfect CSI scenario, as well as the complexity and non-convexity of the problem, we propose a deep reinforcement learning method to simultaneously design transmit beamforming and MA movement to against eavesdropper. The simulation results show that the use of MAs improves the secrecy rate by 40% and the proposed algorithm outperforms baseline methods in terms of adaptability and performance.