Impact Analysis of Cyber-Physical Attacks on a Water Tank System via Statistical Model Checking

Cyber-Physical Systems (CPSs) are integrations of distributed computing systems with physical processes that monitor and control entities in a physical environment. Although the range of their applications include several critical domains, the current trend is to verify CPSs with simulation-test systems rather than formal methodologies. In this paper, we test the effectiveness of statistical model checking, within the MODEST TOOLSET, when analyzing the security of a non-trivial quadruple-tank water system equipped with an ad-hoc intrusion detection system (IDS) capable of mitigating attacks. Our goal is to evaluate the impact of three carefully chosen cyber-physical attacks, i.e., attacks targeting sensors and/or actuators of the system with potential consequences on the safety of the inner physical process. Our security analysis estimates both the physical impact of the attacks and the performance of the proposed IDS.