Evaluating Automated Driving Planner Robustness against Adversarial Influence
This addresses the critical need for robust evaluation methods in autonomous driving to ensure safety against adversarial threats, representing an incremental advancement in adversarial evaluation practices.
The paper tackles the problem of evaluating automated driving planner robustness against adversarial agents by proposing an approach based on probabilistic trust models to assess protections for machine learning-enabled planners, demonstrating it on camera-based object detectors.
Evaluating the robustness of automated driving planners is a critical and challenging task. Although methodologies to evaluate vehicles are well established, they do not yet account for a reality in which vehicles with autonomous components share the road with adversarial agents. Our approach, based on probabilistic trust models, aims to help researchers assess the robustness of protections for machine learning-enabled planners against adversarial influence. In contrast with established practices that evaluate safety using the same evaluation dataset for all vehicles, we argue that adversarial evaluation fundamentally requires a process that seeks to defeat a specific protection. Hence, we propose that evaluations be based on estimating the difficulty for an adversary to determine conditions that effectively induce unsafe behavior. This type of inference requires precise statements about threats, protections, and aspects of planning decisions to be guarded. We demonstrate our approach by evaluating protections for planners relying on camera-based object detectors.