对抗样本(论文解读十)：Evading Real-Time Person Detectors by Adversarial T-shirt

最新推荐文章于 2024-04-06 13:24:29 发布

Enjoy_endless

最新推荐文章于 2024-04-06 13:24:29 发布

阅读量2.3k

点赞数

CC 4.0 BY-SA版权

分类专栏：对抗样本 Machine learning Deep learning

本文链接：https://blog.youkuaiyun.com/Enjoy_endless/article/details/103937796

本文介绍了一种新型物理对抗攻击——对抗T恤，能有效躲避人体检测器，即使在穿着者运动导致T恤变形的情况下也具有高鲁棒性。通过对薄板样条(TPS)变换的运用，该研究成功模拟了非刚性物体的变形，实现了对YOLOv2及Faster R-CNN等检测器的同时攻击。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Evading Real-Time Person Detectors by Adversarial T-shirt

Kaidi Xu1 Gaoyuan Zhang2 Sijia Liu2 Quanfu Fan2 Mengshu Sun1 Hongge Chen3 Pin-Yu Chen2 Yanzhi Wang1 Xue Lin1

1Northeastern University, USA 2MIT-IBM Watson AI Lab, IBM Research, USA 3Massachusetts Institute of Technology, USA

论文公开于October 25, 2019

Abstract

现有的物理对抗攻击大多集中在静态物体上，如眼镜框、停止标志和附在硬纸板上的图像。在这里，我们提出了对抗T恤，一个鲁棒的物理对抗样本用于躲避人体检测器。即使因人的姿势变换导致T恤变形，其仍具有较高的鲁棒性。我们首先对变形的影响进行建模，以设计针对t恤等非刚性物体的物理对抗实例。进一步的利用最小/最大优化，其可以同时攻击YOLOv2及Faster R-CNN.

1 Introduction
Early works studied adversarial examples in the digital space only. Recently, some works showed that it is possible to create adversarial perturbations on physical objects … However, most of the studied physical adversarial attacks encounter two limitations: a)通常考虑静态图像 b)忽略了移动目标造成的形变。 In this paper, we propose a new type of physical adversarial attack, adversarial T-shirt, to evade 引出

Most of the existing physical adversarial attacks were generated against image classiﬁers and object detectors. 人脸识别、stop sign、镜头贴条，EOT：旋转、平移、对比度、光照及随机噪声等。 Compared to attacki