Synthesis-guided Adversarial Scenario Generation for Gray-box Feedback Control Systems with Sensing Imperfections

TL;DR

This paper introduces a synthesis-guided algorithm for generating adversarial scenarios in gray-box feedback control systems with sensing imperfections, revealing vulnerabilities and safety violations that are hard to detect with random testing.

Contribution

It presents a novel synthesis-guided method leveraging plant models to identify system vulnerabilities under imperfect information, extending to model mismatch and vision-in-the-loop systems.

Findings

Successfully finds complex safety-violating scenarios

Reveals the impact of sensing imperfections on system safety

Extends to systems with model mismatch and vision-based feedback

Abstract

In this paper, we study feedback dynamical systems with memoryless controllers under imperfect information. We develop an algorithm that searches for "adversarial scenarios", which can be thought of as the strategy for the adversary representing the noise and disturbances, that lead to safety violations. The main challenge is to analyze the closed-loop system's vulnerabilities with a potentially complex or even unknown controller in the loop. As opposed to commonly adopted approaches that treat the system under test as a black-box, we propose a synthesis-guided approach, which leverages the knowledge of a plant model at hand. This hence leads to a way to deal with gray-box systems (i.e., with known plant and unknown controller). Our approach reveals the role of the imperfect information in the violation. Examples show that our approach can find non-trivial scenarios that are difficult to expose by random simulations. This approach is further extended to incorporate model mismatch and to falsify vision-in-the-loop systems against finite-time reach-avoid specifications.