Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910908272345088 |
|---|---|
| author | Jiang, Qingchao Xu, Zhishuo Zhu, Zhiying Chen, Ning Wang, Haoyue Ba, Zhongjie |
| author_facet | Jiang, Qingchao Xu, Zhishuo Zhu, Zhiying Chen, Ning Wang, Haoyue Ba, Zhongjie |
| contents | Advances in image generation enable hyper-realistic synthetic faces but also pose risks, thus making synthetic face detection crucial. Previous research focuses on the general differences between generated images and real images, often overlooking the discrepancies among various generative techniques. In this paper, we explore the intrinsic relationship between synthetic images and their corresponding generation technologies. We find that specific images exhibit significant reconstruction discrepancies across different generative methods and that matching generation techniques provide more accurate reconstructions. Based on this insight, we propose a Multi-Reconstruction-based detector. By reversing and reconstructing images using multiple generative models, we analyze the reconstruction differences among real, GAN-generated, and DM-generated images to facilitate effective differentiation. Additionally, we introduce the Asian Synthetic Face Dataset (ASFD), containing synthetic Asian faces generated with various GANs and DMs. This dataset complements existing synthetic face datasets. Experimental results demonstrate that our detector achieves exceptional performance, with strong generalization and robustness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_07382 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction Jiang, Qingchao Xu, Zhishuo Zhu, Zhiying Chen, Ning Wang, Haoyue Ba, Zhongjie Computer Vision and Pattern Recognition Advances in image generation enable hyper-realistic synthetic faces but also pose risks, thus making synthetic face detection crucial. Previous research focuses on the general differences between generated images and real images, often overlooking the discrepancies among various generative techniques. In this paper, we explore the intrinsic relationship between synthetic images and their corresponding generation technologies. We find that specific images exhibit significant reconstruction discrepancies across different generative methods and that matching generation techniques provide more accurate reconstructions. Based on this insight, we propose a Multi-Reconstruction-based detector. By reversing and reconstructing images using multiple generative models, we analyze the reconstruction differences among real, GAN-generated, and DM-generated images to facilitate effective differentiation. Additionally, we introduce the Asian Synthetic Face Dataset (ASFD), containing synthetic Asian faces generated with various GANs and DMs. This dataset complements existing synthetic face datasets. Experimental results demonstrate that our detector achieves exceptional performance, with strong generalization and robustness. |
| title | Model Discrepancy Learning: Synthetic Faces Detection Based on Multi-Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.07382 |