Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios

Visual detection is a key task in autonomous driving, and it serves as a crucial foundation for self-driving planning and control. Deep neural networks have achieved promising results in various visual tasks, but they are known to be vulnerable to adversarial attacks. A comprehensive understanding o...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Jung Im Choi, Tian, Qing
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 03.07.2022
Subjects
Artificial neural networks
Classification
Computer vision
Detectors
Localization
Object recognition
Robustness
Sensors
Visual aspects
Online AccessGet full text

Cover

More Information
Summary:Visual detection is a key task in autonomous driving, and it serves as a crucial foundation for self-driving planning and control. Deep neural networks have achieved promising results in various visual tasks, but they are known to be vulnerable to adversarial attacks. A comprehensive understanding of deep visual detectors' vulnerability is required before people can improve their robustness. However, only a few adversarial attack/defense works have focused on object detection, and most of them employed only classification and/or localization losses, ignoring the objectness aspect. In this paper, we identify a serious objectness-related adversarial vulnerability in YOLO detectors and present an effective attack strategy targeting the objectness aspect of visual detection in autonomous vehicles. Furthermore, to address such vulnerability, we propose a new objectness-aware adversarial training approach for visual detection. Experiments show that the proposed attack targeting the objectness aspect is 45.17% and 43.50% more effective than those generated from classification and/or localization losses on the KITTI and COCO traffic datasets, respectively. Also, the proposed adversarial defense approach can improve the detectors' robustness against objectness-oriented attacks by up to 21% and 12% mAP on KITTI and COCO traffic, respectively.
ISSN:2331-8422