Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

arXiv:2403.17301v1 Announce Type: cross
Abstract: Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patches, so they only affect a small, localized region in the MDE map but fail under various viewpoints. To address these limitations, we propose 3D Depth Fool (3D$^2$Fool), the first 3D texture-based adversarial attack against MDE models. 3D$^2$Fool is specifically optimized to generate 3D adversarial textures …

adversarial adversarial attacks arxiv attacks autonomous autonomous driving cs.cr cs.cv deep learning driving fail map patches physical physical attacks vulnerable