DeepAI AI Chat
Log In Sign Up

Attacking Motion Estimation with Adversarial Snow

by   Jenny Schmalfuss, et al.
University of Stuttgart

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.


page 1

page 2

page 4


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

Recent optical flow methods are almost exclusively judged in terms of ac...

Attacking Optical Flow

Deep neural nets achieve state-of-the-art performance on the problem of ...

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

Recent work demonstrated the lack of robustness of optical flow networks...

Consistent Semantic Attacks on Optical Flow

We present a novel approach for semantically targeted adversarial attack...

CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks

While neural networks allow highly accurate predictions in many tasks, t...

Unsupervised Hierarchical Domain Adaptation for Adverse Weather Optical Flow

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

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

Automatic optimization of robotic behavior has been the long-standing go...