Deepfake Detection on FaceShifter (FSh)
99.7AUCRealForensics
Evaluation results
| Method | Links | |
|---|---|---|
| RealForensicsTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 99.7 | |
| FTCNTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 98.8 | |
| LipForensicsTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 97.1 | |
| Face X-rayTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 92.8 | |
| DefakerOneModel Category=MLLMs2026.05 | 92.5 | |
| EffortModel Category=Vision Models2026.05 | 88.9 | |
| CSNTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 87.9 | |
| CNN-GRUTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 80.8 | |
| CDFAModel Category=Vision Models2026.05 | 77.7 | |
| XceptionTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 72 | |
| Ivy-xDetectorModel Category=MLLMs2026.05 | 67.3 | |
| Multi-taskTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 66 | |
| CNN-augTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 65.7 | |
| DSP-FWATraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 65.5 | |
| DRCTModel Category=Vision Models2026.05 | 61.6 | |
| Patch-basedTraining Dataset=FaceForensics++, Evaluation Protocol=Cross-dataset generalization2022.01 | 57.8 | |
| TruforModel Category=Vision Models2026.05 | 54 | |
| MesorchModel Category=Vision Models2026.05 | 52.5 | |
| DTDModel Category=Vision Models2026.05 | 50 | |
| FakeVLMModel Category=MLLMs2026.05 | 44.6 | |
| FFDNModel Category=Vision Models2026.05 | 43.1 | |
| ForensicMOEModel Category=MLLMs2026.05 | 41.2 | |
| VeritasModel Category=MLLMs2026.05 | 2.3 |