Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World

Loading...
Thumbnail Image
File version

Version of Record (VoR)

Author(s)
Zhang, H
Hu, S
Wang, Y
Zhang, LY
Zhou, Z
Wang, X
Zhang, Y
Chen, C
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)

Larson, Kate

Date
2024
Size
File type(s)
Location

Jeju, Korea

License
Abstract

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 (~10%-60% absolute and ~2-7x relative) in attack efficacy over state-of-the-art attacks.

Journal Title
Conference Title

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence

Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement

This work is covered by copyright. You must assume that re-use is limited to personal use and that permission from the copyright owner must be obtained for all other uses. If the document is available under a specified licence, refer to the licence for details of permitted re-use. If you believe that this work infringes copyright please make a copyright takedown request using the form at https://www.griffith.edu.au/copyright-matters.

Item Access Status
Note
Access the data
Related item(s)
Subject
Persistent link to this record
Citation

Zhang, H; Hu, S; Wang, Y; Zhang, LY; Zhou, Z; Wang, X; Zhang, Y; Chen, C, Detector Collapse: Backdooring Object Detection to Catastrophic Overload or Blindness in the Physical World, Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024, pp. 1670-1678