Intrusion Detection System with Updated Structure and Feature Selection Algorithm for Man-In- The-Middle Attacks in the Smart Grid

With the rapid development of the smart grid, its vulnerabilities to intentional cyber-attacks are increasingly being exposed. One such attack is the Man-In-The-Middle (MITM) attack, which poses a challenge for online detection due to its stealthy nature. This paper presents an Intrusion Detection System (IDS) with an updated structure to improve the speed. A Random Disturbance Algorithm (RDA) is designed to improve the performance of machine learning blocks. RDA is compared with PCA in its effect on several benchmark algorithms. The proposed IDS is validated in a self-designed testbed that provides both an offline training dataset and an environment for online real-time simulation.