arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.15519cs.CV
收藏

防御针对红外人体检测的物理对抗补丁攻击

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection

University of Freiburg(弗赖堡大学);The University of Tokyo(东京大学);National Institute of Informatics(情报学研究所)

Lukas Strack, Futa Waseda, Huy H. Nguyen, Yinqiang Zheng, Isao Echizen

AI总结:

本文首次研究红外人体检测的对抗补丁防御,提出基于补丁的遮挡感知检测方法POD,通过随机补丁增强训练,在高效检测人员的同时识别补丁位置,并能泛化到未知攻击且提升干净场景下的检测精度。

摘要:

红外检测因其卓越的抗干扰能力,正成为安全关键任务中的新兴技术。然而,近期研究表明,红外检测容易受到物理可实现的对抗补丁攻击,这在其实际应用中带来了风险。为解决这一问题,我们率先研究了针对红外检测(尤其是人体检测)的对抗补丁攻击的防御策略。我们提出了一种直接的防御策略,即基于补丁的遮挡感知检测(POD),该策略通过随机补丁高效地增强训练样本,并随后检测这些补丁。POD不仅能鲁棒地检测人员,还能识别对抗补丁的位置。令人惊讶的是,尽管POD计算效率极高,它却能轻松泛化到训练期间未见过的、最先进的对抗补丁攻击。此外,由于数据增强效应,POD甚至在干净(即无攻击)情况下也能提高检测精度。我们的评估表明,POD对各种形状和尺寸的对抗补丁具有鲁棒性。我们的基线方法的有效性表明,它是现实世界红外人体检测系统的一种可行防御机制,为探索未来的研究方向铺平了道路。

英文摘要:

Infrared detection is an emerging technique for safety-critical tasks owing to its remarkable anti-interference capability. However, recent studies have revealed that it is vulnerable to physically-realizable adversarial patches, posing risks in its real-world applications. To address this problem, we are the first to investigate defense strategies against adversarial patch attacks on infrared detection, especially human detection. We propose a straightforward defense strategy, patch-based occlusion-aware detection (POD), which efficiently augments training samples with random patches and subsequently detects them. POD not only robustly detects people but also identifies adversarial patch locations. Surprisingly, while being extremely computationally efficient, POD easily generalizes to state-of-the-art adversarial patch attacks that are unseen during training. Furthermore, POD improves detection precision even in a clean (i.e., no-attack) situation due to the data augmentation effect. Our evaluation demonstrates that POD is robust to adversarial patches of various shapes and sizes. The effectiveness of our baseline approach is shown to be a viable defense mechanism for real-world infrared human detection systems, paving the way for exploring future research directions.

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。

↑