GNN-Based Online Resource Allocation for RIS-Enabled Covert Communication and Sensing Under Target Mobility

Abstract

This letter investigates a dynamic sensing and covert communication network enabled by a reconfigurable intelligent surface (RIS), where a base station continuously senses an illegal autonomous aerial vehicle (AAV) and utilizes the sensing signals to achieve covert transmission for legitimate ground users. To address the time-varying target states induced by AAV motion, this letter employs an extended Kalman filter (EKF) to perform real-time estimation of the AAV’s 3D position. Then, a covert rate maximization problem is formulated with sensing performance, transmit power, and covertness constraints. To tackle this non-convex problem, a dynamic online resource allocation scheme based on a graph neural network (GNN) is proposed. By leveraging heterogeneous graph features and a constraint-aware loss function, the proposed GNN scheme optimizes the communication and sensing beamforming vectors and the RIS phase shifts. Simulation results show the superiority of the proposed scheme in terms of covert rate. Compared with the alternating optimization scheme, the proposed scheme achieves a 22% improvement in covert rate.