论文标题
仅一刻：深度动作识别对一个框架攻击的结构脆弱性
Just One Moment: Structural Vulnerability of Deep Action Recognition against One Frame Attack
论文作者
论文摘要
近年来，基于视频的动作识别任务已经进行了广泛的研究。在本文中，我们使用一个框架攻击研究了针对对抗性攻击的深度学习动作识别模型的结构脆弱性，该攻击仅为给定视频剪辑的单个框架增加了不明显的扰动。我们的分析表明，由于其结构属性，模型对一个框架攻击非常脆弱。实验表明攻击的愚蠢率和不起眼的特征。此外，我们表明在各种情况下都可以获得强大的通用一帧扰动。我们的工作提出了一个严重的问题，即最先进的行动识别模型的对抗性脆弱性。
The video-based action recognition task has been extensively studied in recent years. In this paper, we study the structural vulnerability of deep learning-based action recognition models against the adversarial attack using the one frame attack that adds an inconspicuous perturbation to only a single frame of a given video clip. Our analysis shows that the models are highly vulnerable against the one frame attack due to their structural properties. Experiments demonstrate high fooling rates and inconspicuous characteristics of the attack. Furthermore, we show that strong universal one frame perturbations can be obtained under various scenarios. Our work raises the serious issue of adversarial vulnerability of the state-of-the-art action recognition models in various perspectives.
