Distracting Downpour: Adversarial Weather Attacks for Motion Estimation
This addresses a realistic threat scenario for autonomous driving and robotics by exposing vulnerabilities in motion estimation systems to adversarial weather, though it is incremental in extending adversarial attacks to more naturalistic conditions.
The paper tackles the problem of adversarial attacks on motion estimation by introducing a novel attack that uses adversarially optimized particles to mimic realistic weather effects like snow, rain, or fog, which significantly impacts motion estimation performance, with methods previously robust to small perturbations showing particular vulnerability.
Current adversarial attacks on motion estimation, or optical flow, optimize small per-pixel perturbations, which are unlikely to appear in the real world. In contrast, adverse weather conditions constitute a much more realistic threat scenario. Hence, in this work, we present a novel attack on motion estimation that exploits adversarially optimized particles to mimic weather effects like snowflakes, rain streaks or fog clouds. At the core of our attack framework is a differentiable particle rendering system that integrates particles (i) consistently over multiple time steps (ii) into the 3D space (iii) with a photo-realistic appearance. Through optimization, we obtain adversarial weather that significantly impacts the motion estimation. Surprisingly, methods that previously showed good robustness towards small per-pixel perturbations are particularly vulnerable to adversarial weather. At the same time, augmenting the training with non-optimized weather increases a method's robustness towards weather effects and improves generalizability at almost no additional cost. Our code will be available at https://github.com/cv-stuttgart/DistractingDownpour.