Graph Neural Networks for Physical-Layer Security in Multi-User Flexible-Duplex Networks

This paper explores Physical-Layer Security (PLS) in Flexible Duplex (FlexD) networks, considering scenarios involving eavesdroppers. Our investigation revolves around the intricacies of the sum secrecy rate maximization problem, particularly when faced with coordinated and distributed eavesdroppers employing a minimum mean square error (MMSE) receiver. Our contributions include an iterative classical optimization solution and a graph neural network (GNNs) based unsupervised learning strategy. To the best of our knowledge, this work marks the initial exploration of GNNs for joint resource allocation for PLS applications. We also extend the GNN approach to address the absence of eavesdroppers' channel knowledge. Extensive numerical simulations highlight FlexD's superiority over half-duplex (HD) communications and the GNN approach's superiority in performance and time complexity over classical methods.