FCA: Learning a 3D Full-Coverage Vehicle Camouflage for Multi-View Physical Adversarial Attack

Author:

Wang Donghua,Jiang Tingsong,Sun Jialiang,Zhou Weien,Gong Zhiqiang,Zhang Xiaoya,Yao Wen,Chen Xiaoqian

Abstract

Physical adversarial attacks in object detection have attracted increasing attention. However, most previous works focus on hiding the objects from the detector by generating an individual adversarial patch, which only covers the planar part of the vehicle’s surface and fails to attack the detector in physical scenarios for multi-view, long-distance and partially occluded objects. To bridge the gap between digital attacks and physical attacks, we exploit the full 3D vehicle surface to propose a robust Full-coverage Camouflage Attack (FCA) to fool detectors. Specifically, we first try rendering the nonplanar camouflage texture over the full vehicle surface. To mimic the real-world environment conditions, we then introduce a transformation function to transfer the rendered camouflaged vehicle into a photo-realistic scenario. Finally, we design an efficient loss function to optimize the camouflage texture. Experiments show that the full-coverage camouflage attack can not only outperform state-of-the-art methods under various test cases but also generalize to different environments, vehicles, and object detectors.

Publisher

Association for the Advancement of Artificial Intelligence (AAAI)

Subject

General Medicine

Cited by 33 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Adversarial infrared blocks: A multi-view black-box attack to thermal infrared detectors in physical world;Neural Networks;2024-07

2. QRPatch: A Deceptive Texture-Based Black-Box Adversarial Attacks with Genetic Algorithm;2024 IEEE Congress on Evolutionary Computation (CEC);2024-06-30

3. Multiview Consistent Physical Adversarial Camouflage Generation through Semantic Guidance;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

4. AdvOcl: Naturalistic Clothing Pattern Adversarial to Person Detectors in Occlusion;Proceedings of the 2024 ACM Workshop on Information Hiding and Multimedia Security;2024-06-24

5. Generate Transferable Adversarial Physical Camouflages via Triplet Attention Suppression;International Journal of Computer Vision;2024-06-01

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3