当前位置: X-MOL 学术IEEE Trans. Pattern Anal. Mach. Intell. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Adversarial Sticker: A Stealthy Attack Method in the Physical World
IEEE Transactions on Pattern Analysis and Machine Intelligence ( IF 23.6 ) Pub Date : 2022-05-23 , DOI: 10.1109/tpami.2022.3176760
Xingxing Wei 1 , Ying Guo 1 , Jie Yu 1
Affiliation  

To assess the vulnerability of deep learning in the physical world, recent works introduce adversarial patches and apply them on different tasks. In this paper, we propose another kind of adversarial patch: the Meaningful Adversarial Sticker, a physically feasible and stealthy attack method by using real stickers existing in our life. Unlike the previous adversarial patches by designing perturbations, our method manipulates the sticker's pasting position and rotation angle on the objects to perform physical attacks. Because the position and rotation angle are less affected by the printing loss and color distortion, adversarial stickers can keep good attacking performance in the physical world. Besides, to make adversarial stickers more practical in real scenes, we conduct attacks in the black-box setting with the limited information rather than the white-box setting with all the details of threat models. To effectively solve for the sticker's parameters, we design the Region based Heuristic Differential Evolution Algorithm, which utilizes the new-found regional aggregation of effective solutions and the adaptive adjustment strategy of the evaluation criteria. Our method is comprehensively verified in the face recognition and then extended to the image retrieval and traffic sign recognition. Extensive experiments show the proposed method is effective and efficient in complex physical conditions and has a good generalization for different tasks.

中文翻译:

Adversarial Sticker:物理世界中的一种隐身攻击方法

为了评估深度学习在物理世界中的脆弱性,最近的工作引入了对抗补丁并将其应用于不同的任务。在本文中,我们提出了另一种对抗性补丁:有意义的对抗性贴纸,这是一种利用我们生活中存在的真实贴纸的物理上可行且隐蔽的攻击方法。与之前通过设计扰动的对抗性补丁不同,我们的方法操纵贴纸在物体上的粘贴位置和旋转角度来执行物理攻击。由于位置和旋转角度受印刷损失和颜色失真的影响较小,因此对抗性贴纸可以在物理世界中保持良好的攻击性能。此外,为了使对抗性贴纸在真实场景中更加实用,我们在信息有限的黑盒环境中进行攻击,而不是在包含威胁模型所有细节的白盒环境中进行攻击。为了有效求解贴纸的参数,我们设计了基于区域的启发式差分进化算法,该算法利用了新发现的有效解的区域聚集和评价标准的自适应调整策略。我们的方法在人脸识别中得到全面验证,然后扩展到图像检索和交通标志识别。大量实验表明,所提出的方法在复杂的物理条件下是有效和高效的,并且对不同的任务具有良好的泛化能力。我们设计了基于区域的启发式差分进化算法,该算法利用了新发现的有效解的区域聚集和评价标准的自适应调整策略。我们的方法在人脸识别中得到全面验证,然后扩展到图像检索和交通标志识别。大量实验表明,所提出的方法在复杂的物理条件下是有效和高效的,并且对不同的任务具有良好的泛化能力。我们设计了基于区域的启发式差分进化算法,该算法利用了新发现的有效解的区域聚集和评价标准的自适应调整策略。我们的方法在人脸识别中得到全面验证,然后扩展到图像检索和交通标志识别。大量实验表明,所提出的方法在复杂的物理条件下是有效和高效的,并且对不同的任务具有良好的泛化能力。
更新日期:2022-05-23
down
wechat
bug