Machine Learning Methods for Attack Detection in the Smart Grid

TL;DR

This paper explores machine learning techniques for detecting cyber-attacks in smart grids, leveraging statistical and geometric analysis to improve detection accuracy over traditional methods, validated on IEEE test systems.

Contribution

It introduces a novel attack detection framework that integrates prior system knowledge with advanced machine learning algorithms for enhanced security.

Findings

Machine learning algorithms outperform traditional state vector estimation methods in attack detection.

The framework effectively detects unobservable attacks using statistical learning.

Experimental results on IEEE test systems validate the approach's robustness and accuracy.

Abstract

Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used to classify measurements as being either secure or attacked. An attack detection framework is provided to exploit any available prior knowledge about the system and surmount constraints arising from the sparse structure of the problem in the proposed approach. Well-known batch and online learning algorithms (supervised and semi-supervised) are employed with decision and feature level fusion to model the attack detection problem. The relationships between statistical and geometric properties of attack vectors employed in the attack scenarios and learning algorithms are analyzed to detect unobservable attacks using statistical learning methods. The proposed algorithms are examined on various IEEE test systems. Experimental analyses show that machine learning algorithms can detect attacks with performances higher than the attack detection algorithms which employ state vector estimation methods in the proposed attack detection framework.