DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910128391847936 |
|---|---|
| author | Giakoumoglou, Paschalis Papadopoulos, Symeon |
| author_facet | Giakoumoglou, Paschalis Papadopoulos, Symeon |
| contents | Modern diffusion-based inpainting models pose significant challenges for image forgery localization (IFL), as their full regeneration pipelines reconstruct the entire image via a latent decoder, disrupting the camera-level noise patterns that existing forensic methods rely on. We propose DiffusionPrint, a patch-level contrastive learning framework that learns a forensic signal robust to the spectral distortions introduced by latent decoding. It exploits the fact that inpainted regions generated by the same model share a consistent generative fingerprint, using this as a self-supervisory signal. DiffusionPrint trains a convolutional backbone via a MoCo-style objective with cross-category hard negative mining and a generator-aware classification head, producing a forensic feature map that serves as a highly discriminative secondary modality in fusion-based IFL frameworks. Integrated into TruFor, MMFusion, and a lightweight fusion baseline, DiffusionPrint consistently improves localization across multiple generative models, with gains of up to +28% on mask types unseen during fine-tuning and confirmed generalization to unseen generative architectures. Code is available at https://github.com/mever-team/diffusionprint |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12443 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization Giakoumoglou, Paschalis Papadopoulos, Symeon Computer Vision and Pattern Recognition Modern diffusion-based inpainting models pose significant challenges for image forgery localization (IFL), as their full regeneration pipelines reconstruct the entire image via a latent decoder, disrupting the camera-level noise patterns that existing forensic methods rely on. We propose DiffusionPrint, a patch-level contrastive learning framework that learns a forensic signal robust to the spectral distortions introduced by latent decoding. It exploits the fact that inpainted regions generated by the same model share a consistent generative fingerprint, using this as a self-supervisory signal. DiffusionPrint trains a convolutional backbone via a MoCo-style objective with cross-category hard negative mining and a generator-aware classification head, producing a forensic feature map that serves as a highly discriminative secondary modality in fusion-based IFL frameworks. Integrated into TruFor, MMFusion, and a lightweight fusion baseline, DiffusionPrint consistently improves localization across multiple generative models, with gains of up to +28% on mask types unseen during fine-tuning and confirmed generalization to unseen generative architectures. Code is available at https://github.com/mever-team/diffusionprint |
| title | DiffusionPrint: Learning Generative Fingerprints for Diffusion-Based Inpainting Localization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.12443 |