On Decidability of Existence of Fortified Supervisors Against Covert Actuator Attackers
Ruochen Tai, Liyong Lin, Rong Su

TL;DR
This paper addresses the problem of synthesizing fortified supervisors that are resilient against covert actuator attackers while preserving the original system behavior, establishing the problem's decidability through a sound and complete procedure.
Contribution
It introduces a decidable method for synthesizing fortified supervisors resilient to covert actuator attackers, extending to worst-case attacker scenarios.
Findings
Decidability of fortified supervisor existence established
Sound and complete synthesis procedure developed
Extension to worst-case attacker scenarios discussed
Abstract
This work investigates the problem of synthesizing fortified supervisors against covert actuator attackers. For a non-resilient supervisor S, i.e., there exists at least a covert actuator attacker that is capable of inflicting damage w.r.t S, a fortified supervisor S' satisfies two requirements: 1) S' is resilient against any covert actuator attacker, and 2) the original closed-behavior of the closed-loop system under S is preserved, that is, S' is control equivalent to S. By designing a sound and complete procedure, we show the problem of determining the existence of a fortified supervisor against covert actuator attackers is decidable. We also discuss how to extend the decidability result to the case against the worst-case attacker.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsSecurity and Verification in Computing · Adversarial Robustness in Machine Learning
