Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
Keywords: Adversarial Training, Monocular Depth Estimation, Adversarial Attack, Self-supervised Learning.
TL;DR: Use self-supervised adversarial training to harden monocular depth estimation models against physical-world adversarial attacks.
Abstract: Monocular Depth Estimation (MDE) is a critical component in applications such as autonomous driving. There are various attacks against MDE networks. These attacks, especially the physical ones, pose a great threat to the security of such systems. Traditional adversarial training method requires ground-truth labels and hence cannot be directly applied to self-supervised MDE that does not have depth ground truth. Some self-supervised model hardening technique (e.g., contrastive learning) ignores the domain knowledge of MDE and can hardly achieve optimal performance. In this work, we propose a novel adversarial training method for self-supervised MDE models based on view synthesis without using the depth ground truth. We improve adversarial robustness against physical-world attacks using $L_0$-norm-bounded perturbation in training. We compare our method with supervised learning-based and contrastive learning-based methods that are tailored for MDE. Results on two representative MDE networks show that we achieve better robustness against various adversarial attacks with nearly no benign performance degradation.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning
Supplementary Material: zip
22 Replies
Loading