Attacking Motion Estimation with Adversarial Snow

10/20/2022
by   Jenny Schmalfuss, et al.
0

Current adversarial attacks for motion estimation (optical flow) optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, we exploit a real-world weather phenomenon for a novel attack with adversarially optimized snow. At the core of our attack is a differentiable renderer that consistently integrates photorealistic snowflakes with realistic motion into the 3D scene. Through optimization we obtain adversarial snow that significantly impacts the optical flow while being indistinguishable from ordinary snow. Surprisingly, the impact of our novel attack is largest on methods that previously showed a high robustness to small L_p perturbations.

READ FULL TEXT

page 1

page 2

page 4

research
05/11/2023

Distracting Downpour: Adversarial Weather Attacks for Motion Estimation

Current adversarial attacks on motion estimation, or optical flow, optim...
research
03/24/2022

A Perturbation Constrained Adversarial Attack for Evaluating the Robustness of Optical Flow

Recent optical flow methods are almost exclusively judged in terms of ac...
research
10/22/2019

Attacking Optical Flow

Deep neural nets achieve state-of-the-art performance on the problem of ...
research
03/30/2021

What Causes Optical Flow Networks to be Vulnerable to Physical Adversarial Attacks

Recent work demonstrated the lack of robustness of optical flow networks...
research
11/16/2021

Consistent Semantic Attacks on Optical Flow

We present a novel approach for semantically targeted adversarial attack...
research
12/16/2019

Evolution of Robust High Speed Optical-Flow-Based Landing for Autonomous MAVs

Automatic optimization of robotic behavior has been the long-standing go...
research
03/24/2023

Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow

Optical flow estimation has made great progress, but usually suffers fro...

Please sign up or login with your details

Forgot password? Click here to reset