Cyber Attack Detection and Trust Management Toolkit for Defence-Related Microgrids

Abstract

AbstractThe rise of microgrids in defence applications, as a greener, more economical and efficient source of energy and the consequential softwarization of networks, has led to the emerge of various cyber-threats. The danger of cyber-attacks in defence microgrid facilities cannot be neglected nor undermined, due to the severe consequences that they can cause. To this end, this paper presents a cyberattack detection and cyber attack severity calculation toolkit, with the aim to provide an end-to-end solution to the cyberattack detection in defense IoT/microgrid systems. Concretely, in this paper are presented and evaluated the SPEAR Visual Analytics AI Engine and the SPEAR Grid Trusted Module (GTM) of the SPEAR H2020 project. The aim of the Visual Analytics AI Engine is to detect malicious action that intend to harm the microgrid and to assist the security engineer of an infrastructure to easily detect abnormalities and submit security events accordingly, while the GTM is responsible to calculate the severity of each security event and to assigns trust values to the affected assets of the system. The accurate detection of cyber-attacks and the efficient reputation management, are assessed with data from a real smart home infrastructure with an installed nanogrid, after applying a 3-stage attack against the MODBUS/TCP protocol used by some of the core nanogrid devices.KeywordsMicrogridsArtificial intelligenceFuzzy logicCyber-attack detection