Department of Mathematics
 Search | Help | Login

Math @ Duke





.......................

.......................


Publications [#386848] of Henry Pfister

Papers Published

  1. Khazraei, A; Pfister, H; Pajic, M, Resiliency of Perception-Based Controllers Against Attacks, Proceedings of Machine Learning Research, vol. 168 (January, 2022), pp. 713-725
    (last updated on 2026/02/08)

    Abstract:
    This work focuses on resiliency of learning-enabled perception-based controllers for nonlinear dynamical systems. We consider systems equipped with an end-to-end controller, mapping the perception (e.g., camera images) and sensor measurements to control inputs, as well as a statistical or learning-based anomaly detector (AD). We define a general notion of attack stealthiness and find conditions for which there exists a sequence of stealthy attacks on perception and sensor measurements that forces the system into unsafe operation without being detected, for any employed AD. Specifically, we show that systems with unstable physical plants and exponentially stable closed-loop dynamics are vulnerable to such stealthy attacks. Finally, we use our results on a case-study.

 

dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821

Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320


x