Physics-Constrained Backdoor Attacks on Power System Fault Localization. (arXiv:2211.04445v1 [cs.CR])

The advances in deep learning (DL) techniques have the potential to deliver
transformative technological breakthroughs to numerous complex tasks in modern
power systems that suffer from increasing uncertainty and nonlinearity.
However, the vulnerability of DL has yet to be thoroughly explored in power
system tasks under various physical constraints. This work, for the first time,
proposes a novel physics-constrained backdoor poisoning attack, which embeds
the undetectable attack signal into the learned model and only performs the
attack when it encounters …

attacks backdoor localization physics power system