Spatial-aware Online Adversarial Perturbations Against Visual Object Tracking

Adversarial attacks of deep neural networks have been intensively studied on image, audio, natural language, patch, and pixel classification tasks. Nevertheless, as a typical, while important real-world application, the adversarial attacks of online video object tracking that traces an object's moving trajectory instead of its category are rarely explored. In this paper, we identify a new task for the adversarial attack to visual object tracking: online generating imperceptible perturbations that mislead trackers along an incorrect (Untargeted Attack, UA) or specified trajectory (Targeted Attack, TA). To this end, we first propose a spatial-aware basic attack by adapting existing attack methods, i.e., FGSM, BIM, and C\&W, and comprehensively analyze the attacking performance. We identify that online object tracking poses two new challenges: 1) it is difficult to generate imperceptible perturbations that can transfer across time/frames, and 2) real-time trackers require the attack to satisfy a certain level of efficiency. To address these challenges, we further propose the online incremental attack (OIA) that performs spatial-temporal sparse incremental perturbations online and makes the adversarial attack less perceptible. In addition, as an optimization-based method, OIA quickly converges to very small losses within several iterations by considering historical incremental perturbations, making it much more efficient than the basic attacks. The in-depth evaluation on the state-of-the-art trackers (i.e., SiamRPN with Alex, MobileNetv2, and ResNet-50) for OTB100 and VOT2018 demonstrates the effectiveness and transferability of OIA in misleading existing trackers under both UA and TA with minor perturbations.