arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.08255cs.CVcs.CR
收藏

针对Segment Anything Models的实用区域级攻击

Practical Region-level Attack against Segment Anything Models

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)

Yifan Shen, Zhengyuan Li, Gang Wang

AI总结:

针对现有SAM对抗攻击威胁模型不现实的问题,提出无需知晓精确用户提示的区域级攻击,结合频谱变换提升黑盒可迁移性,经实验和真实服务验证有效。

摘要:

Segment Anything Models(SAM,分割一切模型)在图像分割领域取得了重大进展,用户只需单次点击(即用户提示)即可分割图像中的目标区域。鉴于其应用广泛,SAM对抗对抗性攻击的鲁棒性是一个关键问题。虽然近期研究已经探索了针对预定义提示/点击的对抗性攻击,但它们的威胁模型尚不具备现实性:(1)它们通常假设攻击者知晓用户点击的位置(基于点的攻击);(2)它们通常在白盒设置下运行,可迁移性有限。本文提出了一种更具实用性的区域级攻击,攻击者无需知晓精确的用户提示。当用户点击图像中目标物体上的任意点时,该攻击仍然有效,可将该物体对SAM隐藏。此外,通过适配频谱变换方法,我们提升了攻击在黑盒设置下的可迁移性。对照实验以及针对真实SAM服务的测试均证实了该攻击的有效性。

英文摘要:

Segment Anything Models (SAM) have made significant advancements in image segmentation, allowing users to segment target portions of an image with a single click (i.e., user prompt). Given its broad applications, the robustness of SAM against adversarial attacks is a critical concern. While recent works have explored adversarial attacks against a pre-defined prompt/click, their threat model is not yet realistic: (1) they often assume the user-click position is known to the attacker (point-based attack), and (2) they often operate under a white-box setting with limited transferability. In this paper, we propose a more practical region-level attack where attackers do not need to know the precise user prompt. The attack remains effective as the user clicks on any point on the target object in the image, hiding the object from SAM. Also, by adapting a spectrum transformation method, we make the attack more transferable under a black-box setting. Both control experiments and testing against real-world SAM services confirm its effectiveness.

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。

↑