GRNN-Based Detection of Eavesdropping Attacks in SWIPT-Enabled Smart Grid Wireless Sensor Networks

This article proposes a novel graph recurrent neural network (GRNN)-based approach for detecting the eavesdropping attacks in smart grid wireless communication systems enabled by simultaneous wireless information and power transfer (SWIPT). By leveraging the graph-centric nature of GRNNs, the proposed method effectively learns the topological structure and the edge features of the wireless sensor networks (WSNs), enabling the detection of the eavesdropping attacks in dynamic WSNs. This article mathematically models the channel state information (CSI) under the man-in-the-middle eavesdropping attacks based on the physical-layer security (PLS) in SWIPT networks. Moreover, this article sets up a real-world testbed to create the training and testing data sets. The proposed GRNN model can handle large-scale complex topologies and dynamic eavesdropping networks, accurately detect eavesdropping behaviors, and enhance the security of information transmission in WSNs. Simulation results demonstrate that, compared with the algorithms, such as support vector machine (SVM), K-nearest neighbors (KNNs), convolutional neural network (CNN), graph convolutional network (GCN), and gated recurrent unit (GRU), the proposed method exhibits stronger robustness under complex attack scenarios, achieving a detection accuracy of over 95%. This article provides a novel and effective graph learning solution for the smart grid wireless communication security, which is of great significance to ensure the stable and reliable operation of the smart grids.