We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Angle Space Adversarial Attack on Skeletal Action Recognition.
- Authors
CAO Nan; DIAO Yunfeng; HUANG Yinqin; DU Run; LI Huaixian; CHENG Tianjian
- Abstract
Deep learning models achieve good performance in skeleton-based action recognition tasks. However, the robustness of skeleton action recognition models has recently been questioned because they are vulnerable to adversarial attacks. At present, the existing white-box attack methods for skeleton action recognition cannot strictly constrain the unique spatial structure of the adversarial skeleton action samples, and the generated adversarial skeleton action samples are non-manifold adversarial samples, that is, the adversarial distribution is far from the original data distribution, which makes the skeleton action unnatural and easy to be perceived by humans. This paper proposes a new angular space adversarial attack method SCA(spherical coordinate attack) that uses spherical coordinate system to represent the skeleton structure. The experimental results on public datasets show that SCA can find most of the adversarial samples in the manifold space, while the existing white-box attack methods for skeleton action recognition can only find the adversarial samples in the non-manifold space.
- Subjects
DEEP learning; RECOGNITION (Psychology); SPHERICAL coordinates; DATA distribution; SKELETON
- Publication
Journal of Computer Engineering & Applications, 2023, Vol 59, Issue 14, p260
- ISSN
1002-8331
- Publication type
Article
- DOI
10.3778/j.issn.1002-8331.2203-0549