Training A Dynamic Neural Network to Detect False Data Injection Attacks Under Multiple Unforeseen Operating Conditions
Published in IEEE Transactions on Smart Grid, 2024
This paper is aimed at addressing the concept drift issue in power system measurements data while detecting FDIAs. It proposes an online self-adptive mechanism to accmodate the traditional attack detection model to unforeseen system operating points.
Recommended citation: Dongping Hu, Shengyang Wu, Jingyu Wang and Dongyuan Shi, "Training a Dynamic Neural Network to Detect False Data Injection Attacks Under Multiple Unforeseen Operating Conditions," IEEE Transactions on Smart Grid, vol. 15, no. 3, pp. 3248-3261.
Download Paper