Result Details
Task: Dual Label Deepfake Video Detection
Analysis Date: 2025-10-06 08:57:21.092471
Information:
Resolution: 576 x 1024 | Codec: h264 | File Size: 3170.59KB | Bitrate: 1028 kbps | Duration: 24.36 seconds | FPS: 23.976 |
Resolution: 576 x 1024 | Codec: h264 | File Size: 3170.59KB | Bitrate: 1028 kbps | Duration: 24.36 seconds | FPS: 23.976 |
Analytic Name: Modality Agnoistic Deepfake Detection
Description: An AVSR-based audio/visual deepfake detection method that leverages speech correlation. The model uses dual-branch encoders for audio and video to support independent detection of each modality.
Code Link:
TBD
🧪 Fake Probability: 94.6%
▲
94.6%
AI-generated Likelihood
Scope: Audio or Videos featuring a single face. A centered, frontal face orientation is preferred, without sunglasses, occlusion, or other visual obstructions.