Fooling Detection Alone is Not Enough: First Adversarial Attack against Multiple Object Tracking
This addresses a critical safety issue for autonomous vehicles by exposing vulnerabilities in the tracking component of perception systems, representing a novel attack paradigm rather than an incremental improvement.
The paper tackles the problem of adversarial attacks on the complete visual perception pipeline in autonomous driving, specifically targeting Multiple Object Tracking (MOT) beyond just object detection, and finds that their novel tracker hijacking technique achieves nearly 100% success rate with attacks on as few as 3 frames, compared to up to 25% for existing detection-only attacks.
Recent work in adversarial machine learning started to focus on the visual perception in autonomous driving and studied Adversarial Examples (AEs) for object detection models. However, in such visual perception pipeline the detected objects must also be tracked, in a process called Multiple Object Tracking (MOT), to build the moving trajectories of surrounding obstacles. Since MOT is designed to be robust against errors in object detection, it poses a general challenge to existing attack techniques that blindly target objection detection: we find that a success rate of over 98% is needed for them to actually affect the tracking results, a requirement that no existing attack technique can satisfy. In this paper, we are the first to study adversarial machine learning attacks against the complete visual perception pipeline in autonomous driving, and discover a novel attack technique, tracker hijacking, that can effectively fool MOT using AEs on object detection. Using our technique, successful AEs on as few as one single frame can move an existing object in to or out of the headway of an autonomous vehicle to cause potential safety hazards. We perform evaluation using the Berkeley Deep Drive dataset and find that on average when 3 frames are attacked, our attack can have a nearly 100% success rate while attacks that blindly target object detection only have up to 25%.