干扰性倾盆大雨：针对运动估计的对抗性天气攻击
Distracting Downpour: Adversarial Weather Attacks for Motion Estimation
AI总结：
提出一种针对运动估计的对抗性天气攻击方法，利用可微粒子渲染系统模拟真实天气效果，发现现有鲁棒方法易受此攻击，而未优化天气数据增强可提升模型鲁棒性与泛化能力。
摘要：
当前针对运动估计（即光流）的对抗性攻击主要优化微小的逐像素扰动，这在现实世界中不太可能出现。相比之下，恶劣天气条件构成了一个更为真实的威胁场景。因此，在本研究中，我们提出了一种针对运动估计的新型攻击方法，该方法利用对抗性优化的粒子来模拟雪花、雨条纹或雾云等天气效果。我们攻击框架的核心是一个可微的粒子渲染系统，该系统将粒子（i）在多个时间步长上一致地（ii）集成到三维空间中（iii）并赋予其照片级真实的外观。通过优化，我们获得了对运动估计产生显著影响的对抗性天气。令人惊讶的是，那些此前对微小逐像素扰动表现出良好鲁棒性的方法，在面对对抗性天气时却显得尤为脆弱。同时，使用未优化的天气数据进行训练增强，能够提高方法对天气效应的鲁棒性，并几乎在不增加额外成本的情况下改善泛化能力。我们的代码将发布在 https://github.com/cv-stuttgart/DistractingDownpour。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
