Cost-Effective Detection of Cyber Physical System Attacks

Abstract

AbstractWith the advancements in modern information and control systems, a new generation of systems has emerged, featuring a combination of independently developed cyber and physical processes. These systems are called cyber physical systems (CPSs). CPSs are composed of various interacting elements that monitor and control the physical processes through a communication network. The various elements include software systems, communication technology, and sensors/actuators that interact with the real world. These systems have impact on every aspect of our society. Hence, they are regarded as critical infrastructure (CI). Security is an issue of prime importance for a CI. More so, because of the impact that it can have in the day-to-day activities. This paper presents an effective defense framework, CPSAD (CPS attack detection framework), which can help detect CPS attacks over optimal feature space. A feature selection module called FSRA (feature selection using rank aggregation) has also been presented to support cost-effective classification of CPS attacks. CPSAD has been tested on several CPS benchmark datasets and the results have been found highly satisfactory.KeywordsCritical infrastructureCyberPhysicalSensorsActuatorsFeature selectionAttacksCPS