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

TL;DR

This paper introduces DepthVanish, a novel adversarial patch design that uses regular interval grid structures to effectively deceive stereo depth estimation systems in both digital and real-world scenarios, including commercial RGB-D cameras.

Contribution

It is the first to optimize adversarial patches with interval structures for physical attacks on stereo depth estimation, improving their practical effectiveness.

Findings

Regular interval grid structures enhance attack success in physical settings.

Optimized patches successfully attack multiple stereo depth methods.

Patches can deceive real-world RGB-D cameras like Intel RealSense.

Abstract

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