Home / AI Research / TwinD: Generalizing Deepfake Detection from Blending to Entire Face Synthesis
TWAI Research
TwinD: Generalizing Deepfake Detection from Blending to Entire Face Synthesis
· Andrii Yermakov, Jan Cech, Mario Fritz, Jiri Matas
Facial deepfake detectors are usually trained on blending fakes, where a generated face is pasted back into a real frame. Recent generators synthesize the entire face and leave no traces of blending. On a benchmark of 19 datasets released from 2019 to 2026, the best prior facial deepfake detector reaches a mean AUROC of 96.2% on ten blending datasets, but none exceeds 78.1% on five datasets of entire face synthesis (EFS). AI-generated content (AIGC) detectors do not close this gap. We propose TwinD, a detector trained on FaceForensics++ fakes and two kinds of twins: fakes made from a real frame. A reconstruction twin is a real frame reconstructed by an autoencoder, with the real pixels put…
Upvotes1
Comments2
Published18 Nov 2026