论文标题
运动兴奋的采样器：带有引发先验的视频对抗攻击
Motion-Excited Sampler: Video Adversarial Attack with Sparked Prior
论文作者
论文摘要
已知深度神经网络容易受到对抗噪声的影响，这些噪声是微小且无法察觉的扰动。以前的对抗攻击的大多数工作主要集中在图像模型上，而视频模型的脆弱性则较少。在本文中，我们旨在通过使用固有的运动模式和视频帧之间的区域相对运动来攻击视频模型。我们提出了一个有效的运动兴奋的采样器，以获得运动吸引的噪声，我们称其为先前的引发。我们的先前引发的强调框架相关性，并通过相对运动利用视频动态。通过在梯度估计中使用Prived Prior，我们可以成功攻击各种查询数量的视频分类模型。四个基准数据集的广泛实验结果验证了我们提出的方法的功效。
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.
