DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cheng, Jikang, Zhang, Ying, Wang, Zhongyuan, Qin, Zou, Li, Chen
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909286114787328
author Cheng, Jikang
Zhang, Ying
Wang, Zhongyuan
Qin, Zou
Li, Chen
author_facet Cheng, Jikang
Zhang, Ying
Wang, Zhongyuan
Qin, Zou
Li, Chen
contents Recent years have seen an increasing interest in physical adversarial attacks, which aim to craft deployable patterns for deceiving deep neural networks, especially for person detectors. However, the adversarial patterns of existing patch-based attacks heavily suffer from the self-coupling issue, where a degradation, caused by physical transformations, in any small patch segment can result in a complete adversarial dysfunction, leading to poor robustness in the complex real world. Upon this observation, we introduce the Decoupled adversarial Patch (DePatch) attack to address the self-coupling issue of adversarial patches. Specifically, we divide the adversarial patch into block-wise segments, and reduce the inter-dependency among these segments through randomly erasing out some segments during the optimization. We further introduce a border shifting operation and a progressive decoupling strategy to improve the overall attack capabilities. Extensive experiments demonstrate the superior performance of our method over other physical adversarial attacks, especially in the real world.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06625
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World
Cheng, Jikang
Zhang, Ying
Wang, Zhongyuan
Qin, Zou
Li, Chen
Computer Vision and Pattern Recognition
Recent years have seen an increasing interest in physical adversarial attacks, which aim to craft deployable patterns for deceiving deep neural networks, especially for person detectors. However, the adversarial patterns of existing patch-based attacks heavily suffer from the self-coupling issue, where a degradation, caused by physical transformations, in any small patch segment can result in a complete adversarial dysfunction, leading to poor robustness in the complex real world. Upon this observation, we introduce the Decoupled adversarial Patch (DePatch) attack to address the self-coupling issue of adversarial patches. Specifically, we divide the adversarial patch into block-wise segments, and reduce the inter-dependency among these segments through randomly erasing out some segments during the optimization. We further introduce a border shifting operation and a progressive decoupling strategy to improve the overall attack capabilities. Extensive experiments demonstrate the superior performance of our method over other physical adversarial attacks, especially in the real world.
title DePatch: Towards Robust Adversarial Patch for Evading Person Detectors in the Real World
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.06625