arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2410.19863cs.CVcs.LG
收藏

打破幻觉:目标检测中对抗性补丁在现实世界中的挑战

Breaking the Illusion: Real-world Challenges for Adversarial Patches in Object Detection

Graz University of Technology(格拉茨工业大学);Complexity Science Hub Vienna(维也纳复杂性科学中心)

Jakob Shack, Katarina Petrovic, Olga Saukh

AI总结:

本研究针对YOLO目标检测网络,在现实世界中测试全局和局部两种对抗性补丁,分析补丁参数对攻击效果的影响,揭示现实条件下攻击面临的挑战,为开发更鲁棒的防御提供依据。

摘要:

对抗性攻击对机器学习系统的鲁棒性和可靠性构成重大威胁,尤其在计算机视觉应用中。本研究调查了对抗性补丁在现实世界中对YOLO目标检测网络的性能。测试了两种攻击:一种可放置在场景内任意位置的补丁——全局补丁,以及另一种旨在与特定目标对象部分重叠以使其从检测中移除的补丁——局部补丁。分析了补丁大小、位置、旋转、亮度和色调等多种因素对对抗性补丁有效性的影响。结果显示这些参数存在显著依赖性,突出了现实条件下维持攻击效果的挑战。学习将数字应用的变换参数与现实世界中测量的参数对齐,仍会导致补丁性能出现高达64%的差异。这些发现强调了理解环境对对抗性攻击影响的重要性,可为实际机器学习应用中更鲁棒防御的开发提供参考。

英文摘要:

Adversarial attacks pose a significant threat to the robustness and reliability of machine learning systems, particularly in computer vision applications. This study investigates the performance of adversarial patches for the YOLO object detection network in the physical world. Two attacks were tested: a patch designed to be placed anywhere within the scene - global patch, and another patch intended to partially overlap with specific object targeted for removal from detection - local patch. Various factors such as patch size, position, rotation, brightness, and hue were analyzed to understand their impact on the effectiveness of the adversarial patches. The results reveal a notable dependency on these parameters, highlighting the challenges in maintaining attack efficacy in real-world conditions. Learning to align digitally applied transformation parameters with those measured in the real world still results in up to a 64\% discrepancy in patch performance. These findings underscore the importance of understanding environmental influences on adversarial attacks, which can inform the development of more robust defenses for practical machine learning applications.

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。

↑