利用局部可控偏振投影欺骗基于偏振的视觉系统

中文摘要 AI 辅助

偏振是光的一项基本属性，可编码与表面形状、材质、光照及观测几何相关的丰富信息。随着单芯片单色/彩色偏振传感器的出现，偏振数据采集变得前所未有的便捷，计算机视觉领域已涌现出大量基于偏振的视觉应用，例如反射消除、偏振三维形状恢复（shape-from-polarization）、透明物体分割和色彩恒常性等。然而，基于偏振的视觉是否易受对抗攻击？如果存在这种脆弱性，是否有可能在物理世界中实施这类攻击且不被人眼察觉？本文向学界警示：基于偏振的视觉存在脆弱性，且其严重程度可能超过基于RGB的视觉。我们通过改造商用LCD投影仪，实现了局部可控的偏振投影，并成功利用该投影欺骗了当前最先进的、用于玻璃分割和色彩恒常性任务的基于偏振的视觉算法。现有的针对RGB视觉的物理攻击往往需要在攻击效果与人眼隐蔽性之间权衡，而基于偏振投影的对抗攻击无需接触目标，且视觉上难以察觉——因为人眼几乎无法分辨被恶意操控的偏振光与普通照明的差异。这给单色和三色领域的基于偏振的视觉都带来了前所未有的风险，对此应给予足够重视并研究应对措施。

英文摘要

Polarization is a fundamental property of light that encodes abundant information regarding surface shape, material, illumination and viewing geometry. The computer vision community has witnessed a blossom of polarization-based vision applications, such as reflection removal, shape-from-polarization, transparent object segmentation and color constancy, partially due to the emergence of single-chip mono/color polarization sensors that make polarization data acquisition easier than ever. However, is polarization-based vision vulnerable to adversarial attacks? If so, is that possible to realize these adversarial attacks in the physical world, without being perceived by human eyes? In this paper, we warn the community of the vulnerability of polarization-based vision, which can be more serious than RGB-based vision. By adapting a commercial LCD projector, we achieve locally controllable polarizing projection, which is successfully utilized to fool state-of-the-art polarization-based vision algorithms for glass segmentation and color constancy. Compared with existing physical attacks on RGB-based vision, which always suffer from the trade-off between attack efficacy and eye conceivability, the adversarial attackers based on polarizing projection are contact-free and visually imperceptible, since naked human eyes can rarely perceive the difference of viciously manipulated polarizing light and ordinary illumination. This poses unprecedented risks on polarization-based vision, both in the monochromatic and trichromatic domain, for which due attentions should be paid and counter measures be considered.

发表机构

• The University of Tokyo（东京大学）
• Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
• Kyoto University（京都大学）

机构由 AI 辅助整理，请以论文原文为准。