AdvMono3D: Advanced Monocular 3D Object Detection with Depth-Aware Robust Adversarial Training
This addresses a critical safety issue for autonomous driving systems by enhancing adversarial robustness, though it builds incrementally on existing adversarial training approaches.
The paper tackles the vulnerability of monocular 3D object detection models to adversarial attacks in autonomous driving by proposing DART3D, a depth-aware robust adversarial training method that improves robustness with AP_R40 gains of 4.415%, 4.112%, and 3.195% on KITTI datasets.
Monocular 3D object detection plays a pivotal role in the field of autonomous driving and numerous deep learning-based methods have made significant breakthroughs in this area. Despite the advancements in detection accuracy and efficiency, these models tend to fail when faced with such attacks, rendering them ineffective. Therefore, bolstering the adversarial robustness of 3D detection models has become a crucial issue that demands immediate attention and innovative solutions. To mitigate this issue, we propose a depth-aware robust adversarial training method for monocular 3D object detection, dubbed DART3D. Specifically, we first design an adversarial attack that iteratively degrades the 2D and 3D perception capabilities of 3D object detection models(IDP), serves as the foundation for our subsequent defense mechanism. In response to this attack, we propose an uncertainty-based residual learning method for adversarial training. Our adversarial training approach capitalizes on the inherent uncertainty, enabling the model to significantly improve its robustness against adversarial attacks. We conducted extensive experiments on the KITTI 3D datasets, demonstrating that DART3D surpasses direct adversarial training (the most popular approach) under attacks in 3D object detection $AP_{R40}$ of car category for the Easy, Moderate, and Hard settings, with improvements of 4.415%, 4.112%, and 3.195%, respectively.