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 hence cannot be directly applied to self-supervised MDE that does not have ground-truth depth. Some self-supervised model hardening techniques (e.g., contrastive learning) ignore 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 ground-truth depth. We improve adversarial robustness against physical-world attacks using L0-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.
翻译:单心深度估计(MDE)是自动驾驶等应用中的一个关键组成部分。 存在对MDE网络的各种袭击。 这些袭击,特别是物理袭击,严重威胁到这些系统的安全。 传统的对抗性培训方法要求地面真实性标签,因此不能直接应用于没有地面真实性深度的自我监督的MDE。 一些自我监督的模型硬化技术(例如对比学习)忽视了MDE的域知识, 很难取得最佳性能。 在这项工作中, 我们提议了一种新的对抗性培训方法, 用于基于视觉合成的自我监督的MDE模型, 而不使用地面真相深度。 我们在培训中使用L0- 诺姆限制的扰动性干扰性来改进对抗物理世界攻击的对抗性强力。 我们比较了我们的方法与为MDE专门设计的基于监督的学习和对比性学习方法。 两个具有代表性的MDE网络的结果显示,我们在各种对抗性攻击中获得了更强的强力,几乎没有良性性性性性性性性退化。