BriefGPT.xyz
Nov, 2020
Just One Moment: 深度行动识别面临的结构性脆弱性对抗单帧攻击
Just One Moment: Inconspicuous One Frame Attack on Deep Action Recognition
HTML
PDF
Jaehui Hwang, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok Lee
TL;DR
本文研究了基于视频的动作识别模型对于单帧干扰攻击的结构性脆弱性，分析发现这些模型由于其结构性质非常容易受到攻击，实验结果显示了很高的攻击成功率和可忽略的干扰特征，从多个角度揭示了现代动作识别模型在对抗攻击方面的严重脆弱性问题。
Abstract
The
video-based action recognition
task has been extensively studied in recent years. In this paper, we study the vulnerability of
deep learning
-based action recognition methods against the
→