TwinD: Generalizing Deepfake Detection from Blending to Entire Face Synthesis
Abstract
TwinD, trained on reconstruction and blob twins derived from real frames, detects both blending and entire-face-synthesis deepfakes, improving AUROC over prior detectors.
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 back in a random region. It targets the neural traces of a decoder. A blob twin blends an altered copy of a real frame with the frame itself, targeting blending artifacts. It needs no generator and no face-shaped mask. Together, these twins provide two complementary forensic cues that generalize to unseen manipulations. TwinDreaches a mean AUROC of 96.3%, 8.9 points above the prior state-of-the-art, with 98.1% on the blending datasets and 95.6% on the EFS datasets. Trained on twins alone, without a deepfake dataset, single models still reach 94.3% on average over three seeds. For reproducibility, the code, trained model, and training data are at: https://github.com/yermandy/TwinD
Community
TwinD: Generalizing Deepfake Detection from Blending to Entire Face Synthesis
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection (2026)
- RoboFake: Are Deepfake Detectors Ready for Humanoid Face Robots? (2026)
- OccJEPA: Occlusion as Masking for Amodal Video Segmentation (2026)
- Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images (2026)
- Unveil the Mask: Jointly-Optimized Diffusion Masked Pretraining for Appearance-Agnostic Operator Verification (2026)
- One Image Is Enough: Self-Generated Supervision for Personalizing Human Video Diffusion at Test Time (2026)
- VidDub: Replacement-Aware Supervision for Two-Step Video Dubbing (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Get this paper in your agent:
hf papers read 2611.25935 Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper