arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.09919cs.CV
收藏

抗对抗攻击的鲁棒跟踪

Robust Tracking against Adversarial Attacks

Shanghai Jiao Tong University(上海交通大学);Tencent AI Lab(腾讯人工智能实验室)

Shuai Jia, Chao Ma, Yibing Song, Xiaokang Yang

摘要:

虽然深度卷积神经网络(CNN)容易受到对抗攻击的攻击,但在构建针对对抗攻击的鲁棒深度跟踪算法方面却付出了相当少的努力。目前对对抗攻击和防御的研究主要集中在单个图像上。在这项工作中,我们首先尝试在视频序列上生成对抗性示例,以提高对对抗攻击的跟踪鲁棒性。为此,我们考虑到时间运动时,生成轻量级的扰动估计跟踪结果逐帧。一方面,我们在原始视频序列中加入时间扰动作为对抗样本,大大降低了跟踪性能。另一方面,我们从输入序列中依次估计扰动,并学习消除它们的影响,以恢复性能。我们将所提出的对抗攻击和防御方法应用于最先进的深度跟踪算法。对基准数据集的广泛评估表明,我们的防御方法不仅消除了对抗攻击造成的大的性能下降,而且在深度跟踪器不受对抗攻击的情况下,还实现了额外的性能增益。

英文摘要:

While deep convolutional neural networks (CNNs) are vulnerable to adversarial attacks, considerably few efforts have been paid to construct robust deep tracking algorithms against adversarial attacks. Current studies on adversarial attack and defense mainly reside in a single image. In this work, we first attempt to generate adversarial examples on top of video sequences to improve the tracking robustness against adversarial attacks. To this end, we take temporal motion into consideration when generating lightweight perturbations over the estimated tracking results frame-by-frame. On one hand, we add the temporal perturbations into the original video sequences as adversarial examples to greatly degrade the tracking performance. On the other hand, we sequentially estimate the perturbations from input sequences and learn to eliminate their effect for performance restoration. We apply the proposed adversarial attack and defense approaches to state-of-the-art deep tracking algorithms. Extensive evaluations on the benchmark datasets demonstrate that our defense method not only eliminates the large performance drops caused by adversarial attacks, but also achieves additional performance gains when deep trackers are not under adversarial attacks.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑