论文标题
对探测器的相关性攻击
Relevance Attack on Detectors
论文作者
论文摘要
本文着重于对探测器的高转移对抗性攻击，由于其多出输出特征和跨体系结构的多样性，这些探测器很难以黑盒方式攻击。追求高攻击性转移性，一种合理的方法是在探测器之间找到一个共同的特性，这有助于发现共同的弱点。我们是第一个建议探测器解释器的相关性图就是这样的属性。基于它，我们设计了对检测器（RAD）的相关性攻击，该攻击可实现最先进的可转移性，超过了20％以上的现有结果。在MS Coco上，所有8个黑盒结构的检测图远远超过一半，并且分割图也受到显着影响。鉴于RAD的极大可传递性，我们生成了第一个以进行对象检测和实例分割的对抗数据集，即上下文中的对抗对象（AOCO），这有助于快速评估和改善检测器的稳健性。
This paper focuses on high-transferable adversarial attacks on detectors, which are hard to attack in a black-box manner, because of their multiple-output characteristics and the diversity across architectures. To pursue a high attack transferability, one plausible way is to find a common property across detectors, which facilitates the discovery of common weaknesses. We are the first to suggest that the relevance map from interpreters for detectors is such a property. Based on it, we design a Relevance Attack on Detectors (RAD), which achieves a state-of-the-art transferability, exceeding existing results by above 20%. On MS COCO, the detection mAPs for all 8 black-box architectures are more than halved and the segmentation mAPs are also significantly influenced. Given the great transferability of RAD, we generate the first adversarial dataset for object detection and instance segmentation, i.e., Adversarial Objects in COntext (AOCO), which helps to quickly evaluate and improve the robustness of detectors.
