Controller confidentiality for nonlinear systems under sensor attacks
Michelle S. Chong

TL;DR
This paper investigates how an adversary can estimate the internal states of a nonlinear control system's controller through sensor attacks, revealing conditions under which confidentiality can be compromised or maintained.
Contribution
It introduces conditions for breaching controller confidentiality in nonlinear systems, including detectability and a novel periodic probing scheme under observability assumptions.
Findings
Controller states can be estimated accurately if the system is detectable.
Confidentiality can be breached via periodic probing under robust observability.
Stealth can be preserved by selecting appropriate probing durations.
Abstract
Controller confidentiality under sensor attacks refers to whether the internal states of the controller can be estimated when the adversary knows the model of the plant and controller, while only having access to sensors, but not the actuators. We show that the controller's state can be estimated accurately when the nonlinear closed-loop system is detectable. In the absence of detectability, controller confidentiality can still be breached with a periodic probing scheme via the sensors under a robust observability assumption, which allows for the controller's state to be estimated with arbitrary accuracy during the probing period, and with bounded error during the non-probing period. Further, stealth can be maintained by choosing an appropriate probing duration. This study shows that the controller confidentiality for nonlinear systems can be breached by balancing the estimation…
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
TopicsFault Detection and Control Systems · Adversarial Robustness in Machine Learning · Smart Grid Security and Resilience
