Result Details
Task: Wav2lip Deepfake Video Model Attribution
Analysis Date: 2025-06-04 10:34:35.976734
Information:
Resolution: 358 x 642 | Codec: h264 | File Size: 1006.82KB | Bitrate: 530 kbps | Duration: 14.17 seconds | FPS: 30.0 |
Resolution: 358 x 642 | Codec: h264 | File Size: 1006.82KB | Bitrate: 530 kbps | Duration: 14.17 seconds | FPS: 30.0 |
Analytic Name: WAV2LIP-STA
Description: Deep learning based method that can identify wav2lip model generated deepfake videos. This method learns the spatial and temporal artifacts from multi-frames (5) to expose wav2lip deepfakes.
Reference:
https://arxiv.org/pdf/2202.12951.pdf
🧪 Fake Probability: 94.34%
â–²
94.34%
AI-generated Likelihood
Scope: Human face videos
Advanced Result:
Download