Open access
Sep 2026
Generalizable Deepfake Detection via Frequency-Domain Enhancement and Feature Disentanglement
A generalizable deepfake detection framework that combines frequency-domain enhancement with feature disentanglement to encourage effective feature disentanglement and improve the discriminability of the learned forgery features is proposed.
Qian Wang, Jia-Qi Feng, Yu Zhou et al.
· Applied Informatics · 0 citations