arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.04781cs.CV
收藏

自动驾驶场景下YOLO探测器的对抗攻击与防御

Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios

Bowling Green State University(鲍灵格林州立大学)

Jung Im Choi, Qing Tian

摘要:

视觉检测是自动驾驶中的一项关键任务,是自动驾驶规划和控制的重要基础。深度神经网络在各种视觉任务中取得了令人鼓舞的成果,但众所周知,它们容易受到对抗攻击的攻击。在人们提高其鲁棒性之前,需要全面了解深度视觉检测器的脆弱性。然而,只有少数对抗攻击/防御工作集中在目标检测,他们中的大多数只采用分类和/或定位损失,忽略了对象方面。在本文中,我们确定了YOLO检测器中一个严重的对象相关对抗漏洞,并针对自动驾驶汽车视觉检测的对象方面提出了一种有效的攻击策略。此外,为了解决这种脆弱性,我们提出了一种新的对象感知对抗训练方法用于视觉检测。实验表明,针对对象方面的攻击是45.17%和43.50%,分别比那些产生的分类和/或本地化损失的KITTI和COCO流量数据集,更有效。此外,所提出的对抗性防御方法可以提高检测器对面向对象攻击的鲁棒性,在KITTI和COCO流量上分别提高21%和12%mAP。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑