PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs

arXiv:2608.18573v1 Announce Type: new Abstract: 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 https://github.com/yqli00000/PATE-Forensics.

Related

• ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization
• Open-Set Visual Text Forensics via Sparse-Constraint Rectified Flow
• DINOv3 Beats Specialized Detectors: A Simple Foundation Model Baseline for Image Forensics
• Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors

Source: arXiv cs.CV | 2026-08-20