CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912077191315456 |
|---|---|
| author | Yang, Shanmin Guo, Hui Hu, Shu Zhu, Bin Fu, Ying Lyu, Siwei Wu, Xi Wang, Xin |
| author_facet | Yang, Shanmin Guo, Hui Hu, Shu Zhu, Bin Fu, Ying Lyu, Siwei Wu, Xi Wang, Xin |
| contents | Deepfake technology poses a significant threat to security and social trust. Although existing detection methods have shown high performance in identifying forgeries within datasets that use the same deepfake techniques for both training and testing, they suffer from sharp performance degradation when faced with cross-dataset scenarios where unseen deepfake techniques are tested. To address this challenge, we propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF). Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. Specifically, it adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination. Moreover, it optimizes these two kinds of information to be independent with a de-correlation learning module, thereby enhancing the model's robustness against various irrelevant information changes and generalization ability to unseen forgery methods. Our extensive experimental evaluation and comparison with existing state-of-the-art detection methods validate the effectiveness and superiority of the DID framework on cross-dataset deepfake detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_00359 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition Yang, Shanmin Guo, Hui Hu, Shu Zhu, Bin Fu, Ying Lyu, Siwei Wu, Xi Wang, Xin Computer Vision and Pattern Recognition Deepfake technology poses a significant threat to security and social trust. Although existing detection methods have shown high performance in identifying forgeries within datasets that use the same deepfake techniques for both training and testing, they suffer from sharp performance degradation when faced with cross-dataset scenarios where unseen deepfake techniques are tested. To address this challenge, we propose a Deep Information Decomposition (DID) framework to enhance the performance of Cross-dataset Deepfake Detection (CrossDF). Unlike most existing deepfake detection methods, our framework prioritizes high-level semantic features over specific visual artifacts. Specifically, it adaptively decomposes facial features into deepfake-related and irrelevant information, only using the intrinsic deepfake-related information for real/fake discrimination. Moreover, it optimizes these two kinds of information to be independent with a de-correlation learning module, thereby enhancing the model's robustness against various irrelevant information changes and generalization ability to unseen forgery methods. Our extensive experimental evaluation and comparison with existing state-of-the-art detection methods validate the effectiveness and superiority of the DID framework on cross-dataset deepfake detection. |
| title | CrossDF: Improving Cross-Domain Deepfake Detection with Deep Information Decomposition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2310.00359 |