FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915811046719488 |
|---|---|
| author | Liu, Zhou Su, Tonghua Zhang, Hongshi Yang, Fuxiang Di, Donglin Song, Yang Fan, Lei |
| author_facet | Liu, Zhou Su, Tonghua Zhang, Hongshi Yang, Fuxiang Di, Donglin Song, Yang Fan, Lei |
| contents | Advances in image tampering techniques, particularly generative models, pose significant challenges to media verification, digital forensics, and public trust. Existing image forgery detection and localization (IFDL) methods suffer from two key limitations: over-reliance on semantic content while neglecting textural cues, and limited interpretability of subtle low-level tampering traces. To address these issues, we propose FOCA, a multimodal large language model-based framework that integrates discriminative features from both the RGB spatial and frequency domains via a cross-attention fusion module. This design enables accurate forgery detection and localization while providing explicit, human-interpretable cross-domain explanations. We further introduce FSE-Set, a large-scale dataset with diverse authentic and tampered images, pixel-level masks, and dual-domain annotations. Extensive experiments show that FOCA outperforms state-of-the-art methods in detection performance and interpretability across both spatial and frequency domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18880 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model Liu, Zhou Su, Tonghua Zhang, Hongshi Yang, Fuxiang Di, Donglin Song, Yang Fan, Lei Computer Vision and Pattern Recognition Artificial Intelligence Advances in image tampering techniques, particularly generative models, pose significant challenges to media verification, digital forensics, and public trust. Existing image forgery detection and localization (IFDL) methods suffer from two key limitations: over-reliance on semantic content while neglecting textural cues, and limited interpretability of subtle low-level tampering traces. To address these issues, we propose FOCA, a multimodal large language model-based framework that integrates discriminative features from both the RGB spatial and frequency domains via a cross-attention fusion module. This design enables accurate forgery detection and localization while providing explicit, human-interpretable cross-domain explanations. We further introduce FSE-Set, a large-scale dataset with diverse authentic and tampered images, pixel-level masks, and dual-domain annotations. Extensive experiments show that FOCA outperforms state-of-the-art methods in detection performance and interpretability across both spatial and frequency domains. |
| title | FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.18880 |