arXiv 2506.166902025-11-03cs.CV

DepthVanish：优化立体深度不可见补丁的对抗性间隔结构

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

University of Alberta（阿尔伯塔大学）；VCIP, CS, Nankai University（VCIP、计算机科学系、南开大学）；NKIARI, Shenzhen Futian（NKIARI、深圳福田）；The University of Tokyo（东京大学）；CFAR and IHPC, Agency for Science, Technology and Research (A*STAR)（CFAR和IHPC、科技研究局（A*STAR））；Nanyang Technological University（南洋理工大学）

Yun Xing, Yue Cao, Nhat Chung, Jie Zhang, Ivor Tsang, Ming-Ming Cheng, Yang Liu, Lei Ma, Qing Guo

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 DepthVanish 方法，通过在重复纹理间引入规则间隔形成网格结构并联合优化间隔与纹理，生成可攻击立体深度估计系统的对抗性补丁，成功在数字和物理环境中误导先进模型及商用 RGB-D 相机。

摘要：

立体深度估计是自动驾驶和机器人技术中的一项关键任务，其中的不准确（例如将近处物体误认为远处）可能导致危险情况。针对立体深度估计的对抗性攻击有助于在部署前揭示漏洞。先前的工作表明，重复优化的纹理可以在数字环境中有效误导立体深度估计。然而，我们的研究表明，这些简单重复的纹理在物理实现中表现不佳，即当作为补丁部署时，限制了它们在压力测试立体深度估计系统方面的实际效用。在这项工作中，我们首次发现，在重复纹理之间引入规则间隔，创建网格结构，能显著增强补丁的攻击性能。通过大量实验，我们分析了这种新结构的变化如何影响对抗有效性。基于这些见解，我们开发了一种新颖的立体深度攻击，联合优化间隔结构和纹理元素。我们生成的对抗性补丁可以插入任何场景，并成功攻击不同范式的先进立体深度估计方法，即 RAFT-Stereo 和 STTR。最关键的是，我们的补丁还能在现实条件下攻击商用 RGB-D 相机（Intel RealSense），证明了它们在立体系统安全评估中的实际相关性。代码已正式发布于：https://github.com/WiWiN42/DepthVanish

英文摘要：

Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situations. Adversarial attacks against stereo depth estimation can help reveal vulnerabilities before deployment. Previous works have shown that repeating optimized textures can effectively mislead stereo depth estimation in digital settings. However, our research reveals that these naively repeated textures perform poorly in physical implementations, i.e., when deployed as patches, limiting their practical utility for stress-testing stereo depth estimation systems. In this work, for the first time, we discover that introducing regular intervals among the repeated textures, creating a grid structure, significantly enhances the patch's attack performance. Through extensive experimentation, we analyze how variations of this novel structure influence the adversarial effectiveness. Based on these insights, we develop a novel stereo depth attack that jointly optimizes both the interval structure and texture elements. Our generated adversarial patches can be inserted into any scenes and successfully attack advanced stereo depth estimation methods of different paradigms, i.e., RAFT-Stereo and STTR. Most critically, our patch can also attack commercial RGB-D cameras (Intel RealSense) in real-world conditions, demonstrating their practical relevance for security assessment of stereo systems. The code is officially released at: https://github.com/WiWiN42/DepthVanish

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。