Object detection plays a key role in many security-critical systems. Adversarial patch attacks, which are easy to implement in the physical world, pose a serious threat to state-of-the-art object detectors. Developing reliable defenses for object detectors against patch attacks is critical but severely understudied. In this paper, we propose Segment and Complete defense (SAC), a general framework for defending object detectors against patch attacks through detection and removal of adversarial patches. We first train a patch segmenter that outputs patch masks which provide pixel-level localization of adversarial patches. We then propose a self adversarial training algorithm to robustify the patch segmenter. In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images if the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth patch masks. Our experiments on COCO and xView datasets demonstrate that SAC achieves superior robustness even under strong adaptive attacks with no reduction in performance on clean images, and generalizes well to unseen patch shapes, attack budgets, and unseen attack methods. Furthermore, we present the APRICOT-Mask dataset, which augments the APRICOT dataset with pixel-level annotations of adversarial patches. We show SAC can significantly reduce the targeted attack success rate of physical patch attacks. Our code is available at https://github.com/joellliu/SegmentAndComplete.
翻译:在许多安全关键系统中, 目标探测是关键。 反偏差攻击在物理世界中很容易执行, 严重威胁到最先进的物体探测器。 开发可靠的物体探测器防补补补丁袭击是关键, 但研究严重不足。 在本文中, 我们提议了部分和完整防御( SAC ), 通过探测和清除对立补丁, 保护物体探测器免遭补丁袭击的一般框架。 我们首先训练一个补丁部分, 以补补上口罩, 提供像素级对抗性补丁的本地化。 然后我们提出一个自我对抗性培训算法, 以强化补丁断裂器。 此外, 我们设计了一个强大的形状完成算术算法, 如果补丁分解器的输出在地面图质封封口的一定距离内, 则可以消除整补补补补补。 我们的CO2 和 xVView数据集显示, 即使在强的适应性攻击下, 清洁图像的性功能不减少, 并且将普通化为可见的补补缺损形状, 攻击预算, 和隐蔽攻击方法也保证从图像上删除整补补补补。 我们ARIIC 数据库 数据库 数据库, 正在 数据库 数据库 数据库 数据库 数据库 数据库 大大显示SOBIS 。