Yihui Wang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1
Frequent co-authors
Research Timeline
2026
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature representations.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIRecentJun 1, 2026
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
Yihui Wang, Yonghui Yang, Jilong Liu, Fengbin Zhu +2 more
The paper proposes the Shortcut Subspace Suppression (S^3) framework to improve deepfake detection generalization by explicitly identifying and suppressing method-specific shortcuts in learned feature…
View →