A Survey of Machine Learning-based Cyber-physical Attack Generation, Detection, and Mitigation in Smart-Grid

Abstract

Cyber-physical (CP) attacks are the principal dangers confronting the usage and advancement of the contemporary smart-grid (SG) system. Advancement of SG has added a wide range of technology, equipment, and tools to make the system more reliable, efficient, and cost-effective. Despite attaining these goals, the threat space for the adversarial attacks has also been expanded because of the addition of the cyber layers. Machine learning (ML) based tools are being used to exploit and defend the system for its massive computational and reasoning capability. In this paper, we perform a comprehensive summary of cyber-physical attack identification and mitigation schemes by reviewing state-of-the-art researches in the SG domain. After that, we address ML assisted attack for facilitating future researchers to get updated about the existing research status. Additionally, we present a tabular form of current researches in a structured way to help the potential forthcoming researchers in deciding their research focus. We also present the shortcomings of the existing works and possible future research direction based on our investigation.