Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Hangtao, Hu, Shengshan, Wang, Yichen, Zhang, Leo Yu, Zhou, Ziqi, Wang, Xianlong, Zhang, Yanjun, Chen, Chao
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866917749642493952
author	Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao
author_facet	Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao
contents	Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks.
format	Preprint
id	arxiv_https___arxiv_org_abs_2404_11357
institution	arXiv
publishDate	2024
record_format	arxiv
spellingShingle	Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving Zhang, Hangtao Hu, Shengshan Wang, Yichen Zhang, Leo Yu Zhou, Ziqi Wang, Xianlong Zhang, Yanjun Chen, Chao Computer Vision and Pattern Recognition Object detection tasks, crucial in safety-critical systems like autonomous driving, focus on pinpointing object locations. These detectors are known to be susceptible to backdoor attacks. However, existing backdoor techniques have primarily been adapted from classification tasks, overlooking deeper vulnerabilities specific to object detection. This paper is dedicated to bridging this gap by introducing Detector Collapse} (DC), a brand-new backdoor attack paradigm tailored for object detection. DC is designed to instantly incapacitate detectors (i.e., severely impairing detector's performance and culminating in a denial-of-service). To this end, we develop two innovative attack schemes: Sponge for triggering widespread misidentifications and Blinding for rendering objects invisible. Remarkably, we introduce a novel poisoning strategy exploiting natural objects, enabling DC to act as a practical backdoor in real-world environments. Our experiments on different detectors across several benchmarks show a significant improvement ($\sim$10\%-60\% absolute and $\sim$2-7$\times$ relative) in attack efficacy over state-of-the-art attacks.
title	Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2404.11357