Metraipolis › archive › dc_f0aebea563d0
PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs — arXiv:2608.18573
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.18573
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T14:06:17.561Z
- SHA-256 of the archived text
8c69ea861319aa9e7b471f97f96bea07148915c2aed88d95393e8286b051dd82- Stable URL of this page
https://metraipolis.com/documento/dc_f0aebea563d0
How to cite
PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs — arXiv:2608.18573 — arXiv (en), https://arxiv.org/abs/2608.18573 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0aebea563d0 (Metraipolis archive dc_f0aebea563d0, sha256 8c69ea861319aa9e7b471f97f96bea07148915c2aed88d95393e8286b051dd82)
BibTeX
@misc{dcf0aebea563d0,
title = {PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs — arXiv:2608.18573},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.18573},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0aebea563d0; sha256 8c69ea861319aa9e7b471f97f96bea07148915c2aed88d95393e8286b051dd82},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.18573. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Existing explainable deepfake forensic methods typically rely on task-adapted MLLM to jointly address detection, localization, and explanation. Inspired by agent-style tool use, we instead introduce a Perception-as-Tool paradigm and instantiate it as PATE-Forensics, which architecturally decouples detection and localization from explanation generation while coupling detection and localization as tightly as possible within a forensic perception tool. The DINOv3-based tool couples a multi-granularity detection module that integrates global, patch-level, and segment-level evidence with a cue-guided localization module by spatializing the patch-level and segment-level evidence into forgery score maps that guide dense mask prediction. The original image and forensic perception outputs produced by the tool form structured forensic context for a general-purpose MLLM, which is guided by prompt constraints to generate explanations without task-specific fine-tuning. On DDL-X Track 3, PATE-Forensics achieves the best official score of 0.89, outperforming the second-ranked team by 0.19 points. Our code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-20 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.18573 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T14:00:22.554Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-20?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).