Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
This addresses security threats in applications like autonomous driving by enhancing model robustness against physical-world attacks, representing an incremental advance over existing methods.
The paper tackles the problem of adversarial attacks on monocular depth estimation models by introducing a self-supervised training approach that uses view synthesis without ground-truth depth, resulting in improved robustness against various attacks with minimal impact on benign performance.
Monocular Depth Estimation (MDE) plays a vital role in applications such as autonomous driving. However, various attacks target MDE models, with physical attacks posing significant threats to system security. Traditional adversarial training methods, which require ground-truth labels, are not directly applicable to MDE models that lack ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) overlook the domain knowledge of MDE, resulting in suboptimal performance. In this work, we introduce a novel self-supervised adversarial training approach for MDE models, leveraging view synthesis without the need for ground-truth depth. We enhance adversarial robustness against real-world attacks by incorporating L_0-norm-bounded perturbation during training. We evaluate our method against supervised learning-based and contrastive learning-based approaches specifically designed for MDE. Our experiments with two representative MDE networks demonstrate improved robustness against various adversarial attacks, with minimal impact on benign performance.