Secure Predictive Beamforming for IRS Enabled ISAC: A Deep Learning Approach

Although integrated sensing and communication (ISAC) has an advantage of mutual gain of its dual functions, it is susceptible to be eavesdropped by mobile targets due to the broadcast nature of wireless channels. In this paper, we propose a secure predictive beamforming scheme against a mobile eavesdropping target for ISAC, where the intelligent reflecting surface (IRS) is utilized to assist the sensing and secure transmission. To tackle the eavesdropping target, we first formulate a sum secrecy rate maximization problem. However, due to the non-convex objective function and the outdated channel state information (CSI), it is difficult to solve the problem directly. Thus, we develop a deep learning based predictive beamforming scheme. It can learn the features from the historical CSI to design the beamformings for the next time slot with low computational complexity. Simulation results show that the proposed scheme can significantly enhance the security of ISAC with low overhead.