ML Research Wiki / Benchmarks / DeepFake Detection / FakeAVCeleb

FakeAVCeleb

DeepFake Detection Benchmark

Performance Over Time

📊 Showing 10 results | 📏 Metric: ROC AUC

Top Performing Models

Rank Model Paper ROC AUC Date Code
1 AV-Lip-Sync+ AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection 99.29 2023-11-05 -
2 Avtenet AVTENet: Audio-Visual Transformer-based Ensemble Network Exploiting Multiple Experts for Video Deepfake Detection 98.57 2023-10-19 -
3 FACTOR Detecting Deepfakes Without Seeing Any 96.80 2023-11-02 📦 talreiss/factor
4 RealForensics Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection 95.30 2022-01-18 📦 ahaliassos/RealForensics
5 AVAD Self-Supervised Video Forensics by Audio-Visual Anomaly Detection 94.20 2023-01-04 📦 cfeng16/audio-visual-forensics
6 FTCN Exploring Temporal Coherence for More General Video Face Forgery Detection 92.30 2021-08-15 📦 yinglinzheng/FTCN
7 LipForensics Lips Don't Lie: A Generalisable and Robust Approach to Face Forgery Detection 89.40 2020-12-14 📦 ahaliassos/lipforensics
8 Xception FaceForensics++: Learning to Detect Manipulated Facial Images 84.80 2019-01-25 📦 ondyari/FaceForensics 📦 polimi-ispl/icpr2020dfdc 📦 yyk-wew/F3Net
9 AVBYOL Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection 73.90 2022-01-18 📦 ahaliassos/RealForensics
10 VQGAN Taming Transformers for High-Resolution Image Synthesis 55.00 2020-12-17 📦 CompVis/taming-transformers 📦 alibaba/EasyNLP 📦 dome272/VQGAN

All Papers (10)

talreiss/factor
ahaliassos/RealForensics
cfeng16/audio-visual-forensics
yinglinzheng/FTCN
ahaliassos/lipforensics
ondyari/FaceForensics polimi-ispl/icpr2020dfdc
ahaliassos/RealForensics
CompVis/taming-transformers alibaba/EasyNLP