- Just one moment: Structural vulnerability of deep action recognition against one frame attack (이종석 교수님 연구실)
- 게시글 내용
Just one moment: Structural vulnerability of deep action recognition against one frame attackIEEE International Conference on Computer Vision (ICCV) (한국연구재단 최우수 CS 학술대회 IF 4)
Jaehui Hwang, Jun-Hyuk Kim, Jun-Ho Choi, Jong-Seok LeeAbstract: 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.