Deep neural networks have made significant advancements in accurately estimating scene flow using point clouds, which is vital for many applications like video analysis, action recognition, and navigation. The robustness of these techniques, however, remains a concern, particularly in the face of adversarial attacks that have been proven to deceive state-of-the-art deep neural networks in many domains. Surprisingly, the robustness of scene flow networks against such attacks has not been thoroughly investigated. To address this problem, the proposed approach aims to bridge this gap by introducing adversarial white-box attacks specifically tailored for scene flow networks. Experimental results show that the generated adversarial examples obtain up to 33.7 relative degradation in average end-point error on the KITTI and FlyingThings3D datasets. The study also reveals the significant impact that attacks targeting point clouds in only one dimension or color channel have on average end-point error. Analyzing the success and failure of these attacks on the scene flow networks and their 2D optical flow network variants shows a higher vulnerability for the optical flow networks. Code is available at https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds.git.

翻译：深度神经网络在利用点云精确估计场景流方面取得了显著进展，这对于视频分析、动作识别和导航等众多应用至关重要。然而，这些技术的鲁棒性仍令人担忧，尤其是在面对对抗性攻击时——此类攻击已被证明能在多个领域欺骗最先进的深度神经网络。令人惊讶的是，场景流网络对此类攻击的鲁棒性尚未得到深入探究。为解决这一问题，本文提出的方法旨在填补这一空白，引入了专门针对场景流网络设计的白盒对抗攻击。实验结果表明，在KITTI和FlyingThings3D数据集上，生成的对抗样本使平均端点误差相对降低了高达33.7%。研究还揭示了仅针对点云单一维度或颜色通道的攻击对平均端点误差产生的显著影响。通过分析这些攻击对场景流网络及其二维光流网络变体的成功与失败案例，发现光流网络具有更高的脆弱性。代码已开源，获取地址为：https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds.git。