A Data Mining-based Intrusion Detection System for Cyber Physical Power Systems

Abstract

The implication of Cyber-physical systems into smart grids has introduced some security breaches due to the lack of security mechanisms. This paper aims to come up with a novel methodology to detect false data injection attacks on cyber-physical power systems. To reach this goal, we propose an efficient anomaly-based approach for detecting false data injection attacks against cyber-physical power systems. Particularly, we use Sequential Pattern Mining techniques, which are commonly used for learning most important patterns of a system. In our case, the frequent pattern learning algorithm is used to create a database corresponding to the normal operation of the system, then, this database is fed into an attack detection algorithm in order to alert the user whenever an attack is occurring. The extensive simulations prove that our attack detection approach is able to detect attacks with a great accuracy.