Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of the image and the detection of one object (or lack thereof) often depends on other objects in the scene. This makes such detectors inherently context-aware and adversarial attacks in this space are more challenging than those targeting image classifiers. In this paper, we present a new approach to generate context-aware attacks for object detectors. We show that by using co-occurrence of objects and their relative locations and sizes as context information, we can successfully generate targeted mis-categorization attacks that achieve higher transfer success rates on blackbox object detectors than the state-of-the-art. We test our approach on a variety of object detectors with images from PASCAL VOC and MS COCO datasets and demonstrate up to $20$ percentage points improvement in performance compared to the other state-of-the-art methods.
翻译:近年来,对图像分类器的黑盒转移攻击进行了广泛研究,相比之下,在物体探测器的转移攻击方面进展甚微。物体探测器对图像进行整体观察,发现一个物体(或缺少)往往取决于现场的其他物体。这使得这种探测器内在的背景意识和对抗性攻击比针对图像分类器的探测器更具挑战性。在本文中,我们提出了一种新方法,为物体探测器制造对背景的认识攻击。我们通过使用物体及其相对位置和大小的共同发生作为背景信息,表明我们能够成功地产生目标错误分类攻击,使黑盒物体探测器的转移成功率高于最新技术。我们用PASAL VOC和MSCO数据集的图像测试了我们的各种物体探测器,并展示了与其他最先进的方法相比,在性能方面高达20美分的改进率。