# Advancing Cyber-Attack Detection in Power Systems: A Comparative Study of Machine Learning and Graph Neural Network Approaches

arXiv: https://arxiv.org/abs/2411.02248 · HTML: https://mlsanity.com/paper/2411.02248/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2024.

## Built on by (most cited first, 3 of 3)

- [CAGN-GAT Fusion: A Hybrid Contrastive Attentive Graph Neural Network for Network Intrusion Detection](https://mlsanity.com/paper/2503.00961/) (2025)
- [Large Language Models for Power System Security: A Novel Multi-Modal Approach for Anomaly Detection in Energy Management Systems](https://mlsanity.com/paper/2508.10044/) (2025)
- [Game-Theoretic Reinforcement Learning based Topology-Agnostic Defense for Virtual Power Plants](https://mlsanity.com/paper/2610.15183/) (2026)

## Abstract (arXiv)

This paper explores the detection and localization of cyber-attacks on time-series measurements data in power systems, focusing on comparing conventional machine learning (ML) like k-means, deep learning method like autoencoder, and graph neural network (GNN)-based techniques. We assess the detection accuracy of these approaches and their potential to pinpoint the locations of specific sensor measurements under attack. Given the demonstrated success of GNNs in other time-series anomaly detection applications, we aim to evaluate their performance within the context of power systems cyber-attacks on sensor measurements. Utilizing the IEEE 68-bus system, we simulated four types of false data attacks, including scaling attacks, additive attacks, and their combinations, to test the selected approaches. Our results indicate that GNN-based methods outperform k-means and autoencoder in detection. Additionally, GNNs show promise in accurately localizing attacks for simple scenarios, although they still face challenges in more complex cases, especially ones that involve combinations of scaling and additive attacks.