Logo image
Back
Adversarial T-Shirt! Evading Person Detectors in a Physical World
Book chapter   Open access   Peer reviewed

Adversarial T-Shirt! Evading Person Detectors in a Physical World

Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan, Mengshu Sun, Hongge Chen, Pin-Yu Chen, Yanzhi Wang and Xue Lin
Computer Vision – ECCV 2020, pp 665-681
29 Oct 2020
DOI: https://doi.org/10.1007/978-3-030-58558-7_39
url
https://arxiv.org/pdf/1910.11099View
SubmittedarXiv.org - Non-exclusive license to distribute,  Open

Abstract

Deep learning Object detection Physical adversarial attack
It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decision makers by attaching adversarial patches to real objects. However, most of the existing works on physical adversarial attacks focus on static objects such as glass frames, stop signs and images attached to cardboard. In this work, we propose Adversarial T-shirts, a robust physical adversarial example for evading person detectors even if it could undergo non-rigid deformation due to a moving person’s pose changes. To the best of our knowledge, this is the first work that models the effect of deformation for designing physical adversarial examples with respect to non-rigid objects such as T-shirts. We show that the proposed method achieves 74% and 57% attack success rates in the digital and physical worlds respectively against YOLOv2. In contrast, the state-of-the-art physical attack method to fool a person detector only achieves 18% attack success rate. Furthermore, by leveraging min-max optimization, we extend our method to the ensemble attack setting against two object detectors YOLO-v2 and Faster R-CNN simultaneously.

Metrics

12 Record Views
222 citations in Scopus

Details

Logo image