arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.06728cs.CV
收藏

对抗性贴纸:物理世界中的隐形攻击方法

Adversarial Sticker: A Stealthy Attack Method in the Physical World

Institute of Artificial Intelligence, Beihang University(北京航空航天大学人工智能研究院);Beihang University(北京航空航天大学)

Xingxing Wei, Ying Guo, Jie Yu

摘要:

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,并将它们应用于不同的任务。在本文中,我们提出了另一种对抗补丁:有意义的对抗贴纸,这是一种物理上可行的隐形攻击方法,使用我们生活中存在的真实贴纸。与以前通过设计扰动的对抗补丁不同,我们的方法操纵贴纸在对象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,为了使对抗贴纸在真实场景中更实用,我们在黑盒设置中使用有限的信息进行攻击,而不是白盒设置中使用威胁模型的所有细节。为了有效地解决贴纸的参数,我们设计了基于区域的启发式差分进化算法,它利用新发现的区域聚集的有效解决方案和自适应调整策略的评价标准。我们的方法在人脸识别中得到了全面的验证,然后扩展到图像检索和交通标志识别。大量的实验表明,该方法在复杂的物理条件下是有效的和高效的,并具有很好的推广到不同的任务。

英文摘要:

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.

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。

↑