A Multi-module Robust Method for Transient Stability Assessment against False Label Injection Cyberattacks

TL;DR

This paper introduces a robust multi-module method for transient stability assessment that effectively detects and corrects false label injections, enhancing deep learning performance under cyberattack conditions.

Contribution

It proposes a novel multi-module framework with an unsupervised label correction and a human-in-the-loop strategy to improve robustness against false label cyberattacks in TSA.

Findings

Demonstrates strong robustness against false label injection attacks.

Effectively corrects contaminated labels in TSA datasets.

Improves accuracy and convergence speed with human-in-the-loop strategy.

Abstract

The success of deep learning in transient stability assessment (TSA) heavily relies on high-quality training data. However, the label information in TSA datasets is vulnerable to contamination through false label injection (FLI) cyberattacks, resulting in degraded performance of deep TSA models. To address this challenge, a Multi-Module Robust TSA method (MMR) is proposed to rectify the supervised training process misguided by FLI in an unsupervised manner. In MMR, a supervised classification module and an unsupervised clustering module are alternatively trained to improve the clustering friendliness of representation leaning, thereby achieving accurate clustering assignments. Leveraging the clustering assignments, we construct a training label corrector to rectify the injected false labels and progressively enhance robustness and resilience against FLI. However, there is still a gap on accuracy and convergence speed between MMR and FLI-free deep TSA models. To narrow this gap, we further propose a human-in-the-loop training strategy, named MMR-HIL. In MMR-HIL, potential false samples can be detected by modeling the training loss with a Gaussian distribution. From these samples, the most likely false samples and most ambiguous samples are re-labeled by a TSA experts guided bi-directional annotator and then subjected to penalized optimization, aimed at improving accuracy and convergence speed. Extensive experiments indicate that MMR and MMR-HIL both exhibit powerful robustness against FLI in TSA performance. Moreover, the contaminated labels can also be effectively corrected, demonstrating superior resilience of the proposed methods.