Back to Search Start Over

Defending Person Detection Against Adversarial Patch Attack by Using Universal Defensive Frame.

Defending Person Detection Against Adversarial Patch Attack by Using Universal Defensive Frame.

Authors :
Yu, Youngjoon
Lee, Hong Joo
Lee, Hakmin
Ro, Yong Man
Source :
IEEE Transactions on Image Processing. 2022, Vol. 31, p6976-6990. 15p.
Publication Year :
2022

Abstract

Person detection has attracted great attention in the computer vision area and is an imperative element in human-centric computer vision. Although the predictive performances of person detection networks have been improved dramatically, they are vulnerable to adversarial patch attacks. Changing the pixels in a restricted region can easily fool the person detection network in safety-critical applications such as autonomous driving and security systems. Despite the necessity of countering adversarial patch attacks, very few efforts have been dedicated to defending person detection against adversarial patch attack. In this paper, we propose a novel defense strategy that defends against an adversarial patch attack by optimizing a defensive frame for person detection. The defensive frame alleviates the effect of the adversarial patch while maintaining person detection performance with clean person. The proposed defensive frame in the person detection is generated with a competitive learning algorithm which makes an iterative competition between detection threatening module and detection shielding module in person detection. Comprehensive experimental results demonstrate that the proposed method effectively defends person detection against adversarial patch attacks. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
10577149
Volume :
31
Database :
Academic Search Index
Journal :
IEEE Transactions on Image Processing
Publication Type :
Academic Journal
Accession number :
170077414
Full Text :
https://doi.org/10.1109/TIP.2022.3217375