Object detection has attracted great attention in the computer vision area and has emerged as an indispensable component in many vision systems. In the era of deep learning, many high-performance object detection networks have been proposed. Although these detection networks show high performance, they are vulnerable to adversarial patch attacks. Changing the pixels in a restricted region can easily fool the detection network in the physical world. In particular, person-hiding attacks are emerging as a serious problem in many safety-critical applications such as autonomous driving and surveillance systems. Although it is necessary to defend against an adversarial patch attack, very few efforts have been dedicated to defending against person-hiding attacks. To tackle the problem, in this paper, we propose a novel defense strategy that mitigates a person-hiding attack by optimizing defense patterns, while previous methods optimize the model. In the proposed method, a frame-shaped pattern called a 'universal white frame' (UWF) is optimized and placed on the outside of the image. To defend against adversarial patch attacks, UWF should have three properties (i) suppressing the effect of the adversarial patch, (ii) maintaining its original prediction, and (iii) applicable regardless of images. To satisfy the aforementioned properties, we propose a novel pattern optimization algorithm that can defend against the adversarial patch. Through comprehensive experiments, we demonstrate that the proposed method effectively defends against the adversarial patch attack.
翻译:在计算机视觉领域,物体探测吸引了计算机视觉领域的极大关注,并已成为许多视觉系统中一个不可或缺的组成部分。在深层次学习的时代,提出了许多高性能物体探测网络。虽然这些探测网络表现出高性能,但它们很容易受到对抗性补丁攻击的伤害。改变限制区域内的像素很容易愚弄物理世界的探测网络。特别是,在诸如自主驾驶和监视系统等许多安全关键应用中,人与人之间的碰撞攻击正在成为一个严重问题。尽管有必要防范对立性补丁攻击,但很少有人专门致力于保护对抗人与人之间的攻击。为了解决这个问题,我们在本文件中提出了一个新的防御战略,通过优化防御模式来减轻对人与人之间的攻击,而以前的方法则优化了这种模式。在拟议的方法中,称为“通用白框架”(UWF)的架式攻击正在形成优化,并置于图像外部。为了防范对立性攻击,UWFF应该具备三种特性:(一) 压制对立性对立性攻击的效果,(二) 保持其最初的预测,以及(三) 通过优化式的模型,我们能够对准。