Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers

Fatemeh Nourilenjan Nokabadi, Jean-Francois Lalonde, Christian Gagné

Keywords: transformer trackers, adversarial robustness, imperceptibility, sparsity

TL;DR: We propose a novel white-box attack for transformer trackers that manipulates a single bounding box to generate adversarial perturbations.

Abstract: Adversarial perturbations aim to deceive neural networks into predicting inaccurate results. For visual object trackers, adversarial attacks have been developed to generate perturbations by manipulating the outputs. However, transformer trackers predict a specific bounding box instead of an object candidate list, which limits the applicability of many existing attack scenarios. To address this issue, we present a novel white-box approach to attack visual object trackers with transformer backbones using only one bounding box. From the tracker predicted bounding box, we generate a list of adversarial bounding boxes and compute the adversarial loss for those bounding boxes. Experimental results demonstrate that our simple yet effective attack outperforms existing attacks against several robust transformer trackers, including TransT-M, ROMTrack, and MixFormer, on popular benchmark tracking datasets such as GOT-10k, UAV123, and VOT2022STS.

Submission Number: 3