Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Wei, Hu, Zhanhao, Li, Xiao, Zhu, Xiaopei, Hu, Xiaolin
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.17322
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911220949319680
author Zhang, Wei
Hu, Zhanhao
Li, Xiao
Zhu, Xiaopei
Hu, Xiaolin
author_facet Zhang, Wei
Hu, Zhanhao
Li, Xiao
Zhu, Xiaopei
Hu, Xiaolin
contents In recent years, adversarial attacks against deep learning-based object detectors in the physical world have attracted much attention. To defend against these attacks, researchers have proposed various defense methods against adversarial patches, a typical form of physically-realizable attack. However, our experiments showed that simply enlarging the patch size could make these defense methods fail. Motivated by this, we evaluated various defense methods against adversarial clothes which have large coverage over the human body. Adversarial clothes provide a good test case for adversarial defense against patch-based attacks because they not only have large sizes but also look more natural than a large patch on humans. Experiments show that all the defense methods had poor performance against adversarial clothes in both the digital world and the physical world. In addition, we crafted a single set of clothes that broke multiple defense methods on Faster R-CNN. The set achieved an Attack Success Rate (ASR) of 96.06% against the undefended detector and over 64.84% ASRs against nine defended models in the physical world, unveiling the common vulnerability of existing adversarial defense methods against adversarial clothes. Code is available at: https://github.com/weiz0823/adv-clothes-break-multiple-defenses.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17322
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World
Zhang, Wei
Hu, Zhanhao
Li, Xiao
Zhu, Xiaopei
Hu, Xiaolin
Computer Vision and Pattern Recognition
In recent years, adversarial attacks against deep learning-based object detectors in the physical world have attracted much attention. To defend against these attacks, researchers have proposed various defense methods against adversarial patches, a typical form of physically-realizable attack. However, our experiments showed that simply enlarging the patch size could make these defense methods fail. Motivated by this, we evaluated various defense methods against adversarial clothes which have large coverage over the human body. Adversarial clothes provide a good test case for adversarial defense against patch-based attacks because they not only have large sizes but also look more natural than a large patch on humans. Experiments show that all the defense methods had poor performance against adversarial clothes in both the digital world and the physical world. In addition, we crafted a single set of clothes that broke multiple defense methods on Faster R-CNN. The set achieved an Attack Success Rate (ASR) of 96.06% against the undefended detector and over 64.84% ASRs against nine defended models in the physical world, unveiling the common vulnerability of existing adversarial defense methods against adversarial clothes. Code is available at: https://github.com/weiz0823/adv-clothes-break-multiple-defenses.
title A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.17322