Adversarial Attacks on Monocular Pose Estimation

07/14/2022
by   Hemang Chawla, et al.
20

Advances in deep learning have resulted in steady progress in computer vision with improved accuracy on tasks such as object detection and semantic segmentation. Nevertheless, deep neural networks are vulnerable to adversarial attacks, thus presenting a challenge in reliable deployment. Two of the prominent tasks in 3D scene-understanding for robotics and advanced drive assistance systems are monocular depth and pose estimation, often learned together in an unsupervised manner. While studies evaluating the impact of adversarial attacks on monocular depth estimation exist, a systematic demonstration and analysis of adversarial perturbations against pose estimation are lacking. We show how additive imperceptible perturbations can not only change predictions to increase the trajectory drift but also catastrophically alter its geometry. We also study the relation between adversarial perturbations targeting monocular depth and pose estimation networks, as well as the transferability of perturbations to other networks with different architectures and losses. Our experiments show how the generated perturbations lead to notable errors in relative rotation and translation predictions and elucidate vulnerabilities of the networks.

READ FULL TEXT

page 1

page 4

research
05/28/2020

Monocular Depth Estimators: Vulnerabilities and Attacks

Recent advancements of neural networks lead to reliable monocular depth ...
research
06/12/2020

Targeted Adversarial Perturbations for Monocular Depth Prediction

We study the effect of adversarial perturbations on the task of monocula...
research
08/18/2019

On the Robustness of Human Pose Estimation

This paper provides, to the best of our knowledge, the first comprehensi...
research
11/02/2019

Security of Facial Forensics Models Against Adversarial Attacks

Deep neural networks (DNNs) have been used in forensics to identify fake...
research
06/17/2019

The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks

Most state-of-the-art machine learning (ML) classification systems are v...
research
08/10/2021

UniNet: A Unified Scene Understanding Network and Exploring Multi-Task Relationships through the Lens of Adversarial Attacks

Scene understanding is crucial for autonomous systems which intend to op...
research
02/25/2021

On Instabilities of Conventional Multi-Coil MRI Reconstruction to Small Adverserial Perturbations

Although deep learning (DL) has received much attention in accelerated M...

Please sign up or login with your details

Forgot password? Click here to reset