Deep neural networks are known to be susceptible to adversarial noise, which are tiny and imperceptible perturbations. Most of previous work on adversarial attack mainly focus on image models, while the vulnerability of video models is less explored. In this paper, we aim to attack video models by utilizing intrinsic movement pattern and regional relative motion among video frames. We propose an effective motion-excited sampler to obtain motion-aware noise prior, which we term as sparked prior. Our sparked prior underlines frame correlations and utilizes video dynamics via relative motion. By using the sparked prior in gradient estimation, we can successfully attack a variety of video classification models with fewer number of queries. Extensive experimental results on four benchmark datasets validate the efficacy of our proposed method.

中文翻译：

---

运动激励采样器：使用 Sparked Prior 进行视频对抗性攻击

众所周知，深度神经网络容易受到对抗性噪声的影响，这是一种微小且难以察觉的扰动。以往关于对抗性攻击的大部分工作主要集中在图像模型上，而对视频模型的漏洞探索较少。在本文中，我们旨在通过利用视频帧之间的内在运动模式和区域相对运动来攻击视频模型。我们提出了一种有效的运动激发采样器来获得运动感知噪声先验，我们将其称为先验激发。我们激发的先验强调了帧相关性，并通过相对运动利用视频动态。通过在梯度估计中使用 sparked 先验，我们可以以较少的查询次数成功攻击各种视频分类模型。在四个基准数据集上的大量实验结果验证了我们提出的方法的有效性。