Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.14554 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918265993822208 |
|---|---|
| author | Romani, Mohammad |
| author_facet | Romani, Mohammad |
| contents | Modern deepfakes evade detection by leaving subtle, domain-speci c artifacts that single branch networks miss. ForensicFlow addresses this by fusing evidence across three forensic dimensions: global visual inconsistencies (via ConvNeXt-tiny), ne-grained texture anomalies (via Swin Transformer-tiny), and spectral noise patterns (via CNN with channel attention). Our attention-based temporal pooling dynamically prioritizes high-evidence frames, while adaptive fusion weights each branch according to forgery type. Trained on CelebDF(v2) with Focal Loss, the model achieves AUC 0.9752, F1 0.9408, and accuracy 0.9208 out performing single-stream detectors. Ablation studies con rm branch synergy, and Grad-CAM visualizations validate focus on genuine manipulation regions (e.g., facial boundaries). This multi-domain fusion strategy establishes robustness against increasingly sophisticated forgeries. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ForensicFlow: A Tri-Modal Adaptive Network for Robust Deepfake Detection Romani, Mohammad Computer Vision and Pattern Recognition Cryptography and Security Machine Learning Modern deepfakes evade detection by leaving subtle, domain-speci c artifacts that single branch networks miss. ForensicFlow addresses this by fusing evidence across three forensic dimensions: global visual inconsistencies (via ConvNeXt-tiny), ne-grained texture anomalies (via Swin Transformer-tiny), and spectral noise patterns (via CNN with channel attention). Our attention-based temporal pooling dynamically prioritizes high-evidence frames, while adaptive fusion weights each branch according to forgery type. Trained on CelebDF(v2) with Focal Loss, the model achieves AUC 0.9752, F1 0.9408, and accuracy 0.9208 out performing single-stream detectors. Ablation studies con rm branch synergy, and Grad-CAM visualizations validate focus on genuine manipulation regions (e.g., facial boundaries). This multi-domain fusion strategy establishes robustness against increasingly sophisticated forgeries. |
| title | ForensicFlow: A Tri-Modal Adaptive Network for Robust Deepfake Detection |
| topic | Computer Vision and Pattern Recognition Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2511.14554 |