Datasets › FakeAVCeleb
FakeAVCeleb
FakeAVCeleb is a novel Audio-Video Deepfake dataset that not only contains deepfake videos but respective synthesized cloned audios as well.
Image source: https://arxiv.org/pdf/2108.05080v1.pdf
Benchmarks archive 2025-07-28
All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| DeepFake Detection | FakeAVCeleb | FACTOR ROC AUC 97.4 | Detecting Deepfakes Without Seeing Any | talreiss/factor | 13 | Compare |
| Multimodal Forgery Detection | FakeAVCeleb | Ensemble AudioVisual Model Accuracy (%) 0.89 | Multimodal Forgery Detection Using Ensemble Learning | ammarahhashmi/Multimodal-Forgery-Detection-Using-Ensemble-Learning | 1 | Compare |
Papers archive 2025-07-28
12 shown of 12 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 65. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
1 loader as listed in the archive; links are outbound and not re-checked here.
Tasks archive 2025-07-28
License archive 2025-07-28
No licence recorded in the archive. Absence here is not a statement about the dataset's terms.
Modalities archive 2025-07-28
Languages archive 2025-07-28
Variants archive 2025-07-28
- FakeAVCeleb
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections