GNN-Based Secrecy Rate Optimization in Multi-Satellite Collaborative Systems

Next-generation satellite systems require efficient collaboration in terms of wide area coverage and signal augmentation, enabling intelligent allocation of available wireless resources to ensure the security of information. Meanwhile, machine learning (ML) is widely considered well-suited to massive, real-time data scenarios in satellite communication networks, and graph neural network (GNN) is a specific branch for processing the irregular data within such networks. In this paper, we propose physical layer security for a multi-satellite collaborative (MSC) system involving LEO satellites, users, and eavesdroppers. Specifically, the GNN-based security communication of the MSC (G-MSC-SC) architecture is designed to maximize the secrecy rate. Since heterogeneous and isomorphic methods can effectively solve multi-type node mapping and complex communication problems, the G-MSC-SC architecture is divided into two steps: A heterogeneous graph pruning attention coefficient network (HGPAN) and an isomorphic graph eavesdropper as an auxiliary node network (IGEAN). In the HGPAN architecture, different types of device nodes are embedded in the same dimensional space, addressing the challenge of matching LEO satellites to users. The IGEAN architecture maps user channel state information (CSI) to beamforming (BF) vectors through attention aggregation and an improved loss function. Moreover, the corresponding conventional optimization algorithms are designed as test and comparison baselines. Simulation results show that 1) the G-MSC-SC architecture outperforms neural networks and heuristic algorithms in terms of accuracy and efficiency; 2) as the numbers of users and virtual eavesdroppers increase, the directional alignment between the BF vectors and the LEO satellite-user channels shows an improvement; and 3) with imperfect CSI, the G-MSC-SC architecture still achieves an excellent balance between user secrecy rate and communication rate.