One-shot adversarial attacks on visual tracking with dual attention

Chen，Xuesong1; Yan，Xiyu2; Zheng，Feng3; Jiang，Yong2; Xia，Shu Tao2,4; Zhao，Yong1; Ji，Rongrong4,5

10.1109/CVPR42600.2020.01019

2020

1063-6919

978-1-7281-7169-2

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

10173-10182

13-19 June 2020

Seattle, WA, USA

Almost all adversarial attacks in computer vision are aimed at pre-known object categories, which could be offline trained for generating perturbations. But as for visual object tracking, the tracked target categories are normally unknown in advance. However, the tracking algorithms also have potential risks of being attacked, which could be maliciously used to fool the surveillance systems. Meanwhile, it is still a challenging task that adversarial attacks on tracking since it has the free-model tracked target. Therefore, to help draw more attention to the potential risks, we study adversarial attacks on tracking algorithms. In this paper, we propose a novel one-shot adversarial attack method to generate adversarial examples for free-model single object tracking, where merely adding slight perturbations on the target patch in the initial frame causes state-of-the-art trackers to lose the target in subsequent frames. Specifically, the optimization objective of the proposed attack consists of two components and leverages the dual attention mechanisms. The first component adopts a targeted attack strategy by optimizing the batch confidence loss with confidence attention while the second one applies a general perturbation strategy by optimizing the feature loss with channel attention. Experimental results show that our approach can significantly lower the accuracy of the most advanced Siamese network-based trackers on three benchmarks.

Target tracking Task analysis Visualization Perturbation methods Object tracking Computer vision Optimization

其他

英语

EI

20204409432070

Computer vision

Computer Applications:723.5 ; Vision:741.2

2-s2.0-85094166630

Scopus

1.Peking University,School of ECE,China
2.Tsinghua University,China
3.Southern University of Science and Technology,China
4.Peng Cheng Laboratory,China
5.Xiamen University,China

Chen，Xuesong,Yan，Xiyu,Zheng，Feng,et al. One-shot adversarial attacks on visual tracking with dual attention[C],2020:10173-10182.