Mitigating Adversarial Attacks on Data-Driven Invariant Checkers for Cyber-Physical Systems
Rajib Ranjan Maiti, Cheah Huei Yoong, Venkata Reddy Palleti, Arlindo Silva, Christopher M. Poskitt
Abstract
The use of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">invariants</i> in developing security mechanisms has become an attractive research area because of their potential to both prevent attacks and detect attacks in Cyber-Physical Systems (CPS). In general, an invariant is a property that is expressed using design parameters along with Boolean operators and which always holds in normal operation of a system, in particular, a CPS. Invariants can be derived by analysing operational data of various design parameters in a running CPS, or by analysing the system's requirements/design documents, with both of the approaches demonstrating significant potential to detect and prevent cyber-attacks on a CPS. While data-driven invariant generation can be fully automated, design-driven invariant generation has a substantial manual intervention. In this paper, we aim to highlight the shortcomings in data-driven invariants by demonstrating a set of adversarial attacks on such invariants. We propose a solution strategy to detect such attacks by complementing them with design-driven invariants. We perform all our experiments on a real water treatment testbed. We shall demonstrate that our approach can significantly reduce false positives and achieve high accuracy in attack detection on CPSs.