Monocular Depth Estimators: Vulnerabilities and Attacks

by   Alwyn Mathew, et al.

Recent advancements of neural networks lead to reliable monocular depth estimation. Monocular depth estimated techniques have the upper hand over traditional depth estimation techniques as it only needs one image during inference. Depth estimation is one of the essential tasks in robotics, and monocular depth estimation has a wide variety of safety-critical applications like in self-driving cars and surgical devices. Thus, the robustness of such techniques is very crucial. It has been shown in recent works that these deep neural networks are highly vulnerable to adversarial samples for tasks like classification, detection and segmentation. These adversarial samples can completely ruin the output of the system, making their credibility in real-time deployment questionable. In this paper, we investigate the robustness of the most state-of-the-art monocular depth estimation networks against adversarial attacks. Our experiments show that tiny perturbations on an image that are invisible to the naked eye (perturbation attack) and corruption less than about 1 introduce a novel deep feature annihilation loss that corrupts the hidden feature space representation forcing the decoder of the network to output poor depth maps. The white-box and black-box test compliments the effectiveness of the proposed attack. We also perform adversarial example transferability tests, mainly cross-data transferability.


page 1

page 5

page 6

page 7

page 11

page 12

page 14

page 15


Adversarial Patch Attacks on Monocular Depth Estimation Networks

Thanks to the excellent learning capability of deep convolutional neural...

Adversarial Attacks on Monocular Pose Estimation

Advances in deep learning have resulted in steady progress in computer v...

Rethinking Monocular Depth Estimation with Adversarial Training

Monocular depth estimation is an extensively studied computer vision pro...

Self-Supervised Learning based Depth Estimation from Monocular Images

Depth Estimation has wide reaching applications in the field of Computer...

Unsupervised Monocular Depth Estimation in Highly Complex Environments

Previous unsupervised monocular depth estimation methods mainly focus on...

Learn to Adapt for Monocular Depth Estimation

Monocular depth estimation is one of the fundamental tasks in environmen...

Analysis of Deep Networks for Monocular Depth Estimation Through Adversarial Attacks with Proposal of a Defense Method

In this paper, we consider adversarial attacks against a system of monoc...

Please sign up or login with your details

Forgot password? Click here to reset