Graph Attention Networks for Invisible Attack Identification in Smart Grids

With the integration of advanced communication and sensor technologies, traditional power grids are shifting to automated smart grids, while exacerbating the risk of cyber-attacks. This paper proposes a spatio-temporal graph attention network to improve invisible attack detection in smart grids. First, graph theory and grid knowledge are utilized for modeling in order to learn graph structure and spatial features. Secondly, hidden features are extracted based on the graph attention mechanism to predict the future behavior of nodes. Thirdly, graph deviation score is calculated from the end-to-end learned node deviations, which is the judgement for identifying attacks. Simulation results demonstrate that our method identify attacks more accurately than baseline methods.