Time-Constrained Intelligent Adversaries for Automation Vulnerability Testing: A Multi-Robot Patrol Case Study
This addresses vulnerability testing for autonomous systems like multi-robot patrols, offering a more realistic adversary model for security evaluation, though it is incremental as it builds on existing simulation and testing frameworks.
The paper tackled the problem of evaluating the robustness of multi-robot patrol systems against hostile attacks by developing a machine learning-based adversary model that observes patrol behavior to gain undetected access within a time limit, showing it outperforms existing baselines and tests multiple patrol strategies.
Simulating hostile attacks of physical autonomous systems can be a useful tool to examine their robustness to attack and inform vulnerability-aware design. In this work, we examine this through the lens of multi-robot patrol, by presenting a machine learning-based adversary model that observes robot patrol behavior in order to attempt to gain undetected access to a secure environment within a limited time duration. Such a model allows for evaluation of a patrol system against a realistic potential adversary, offering insight into future patrol strategy design. We show that our new model outperforms existing baselines, thus providing a more stringent test, and examine its performance against multiple leading decentralized multi-robot patrol strategies.