期刊
2022 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2022)
卷 -, 期 -, 页码 5893-5899出版社
IEEE
DOI: 10.1109/ICRA46639.2022.9812056
关键词
-
资金
- Natural Science Foundation of Shanghai [20ZR1460100]
- National Natural Science Foundation of China [62173249]
This paper proposes a novel adaptive adversarial attack approach to address the potential risk and robustness issues in UAV object tracking. By generating online adversarial examples, the tracker can be fooled and lose track of the target. Experimental results demonstrate the effectiveness of this approach in significantly reducing the performance of state-of-the-art trackers.
Visual tracking is adopted to extensive unmanned aerial vehicle (UAV)-related applications, which leads to a highly demanding requirement on the robustness of UAV trackers. However, adding imperceptible perturbations can easily fool the tracker and cause tracking failures. This risk is often overlooked and rarely researched at present. Therefore, to help increase awareness of the potential risk and the robustness of UAV tracking, this work proposes a novel adaptive adversarial attack approach, i.e., Ad(2)Attack, against UAV object tracking. Specifically, adversarial examples are generated online during the resampling of the search patch image, which leads trackers to lose the target in the following frames. Ad(2)Attack is composed of a direct downsampling module and a super-resolution upsampling module with adaptive stages. A novel optimization function is proposed for balancing the imperceptibility and efficiency of the attack. Comprehensive experiments on several well-known benchmarks and real-world conditions show the effectiveness of our attack method, which dramatically reduces the performance of the most advanced Siamese trackers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据