Deepfake Detection on BleFace
96AUCSePL
Evaluation results
| Method | Links | |
|---|---|---|
| SePLTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 96 | |
| ProDetTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 92.9 | |
| SBITraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 89.1 | |
| SBITraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 89.1 | |
| ForAdaTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 88.8 | |
| SLADDTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 88.2 | |
| VLFFDTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation, Re-implemented=true2026.05 | 87.7 | |
| LSDATraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 87.5 | |
| LSDATraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 87.5 | |
| HAADTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 87.4 | |
| EffortTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 87.3 | |
| X^2-DFDTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation, Re-implemented=true2026.05 | 87.3 | |
| EffortTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation, Re-implemented=true2026.05 | 86.8 | |
| FIA-USATraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation, Re-implemented=true2026.05 | 85.4 | |
| DAIDTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation, Re-implemented=true2026.05 | 84.9 | |
| CORETraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 84.3 | |
| CORETraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 84.3 | |
| RECCETraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 83.2 | |
| RECCETraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 83.2 | |
| UCFTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 82.7 | |
| UCFTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 82.7 | |
| F3NetTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 80.8 | |
| F3NetTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 80.8 | |
| IIDTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 78.9 | |
| IIDTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 78.9 | |
| CDFATraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 75.6 | |
| SPSLTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 74.8 | |
| SPSLTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 74.8 | |
| SRMTraining Dataset=FaceForensics++ (c23), Evaluation Protocol=Cross-method2026.04 | 70.4 | |
| SRMTraining Dataset=FF++, Evaluation Protocol=Cross-method Evaluation2026.05 | 70.4 |