用通用大模型解释深度伪造检测结果，提升可解释性与性能。
PATE-Forensics: Perception-as-Tool for Explainable Deepfake Forensics with General-Purpose MLLMs
- 将检测定位与解释生成解耦，通过感知工具统一处理前两者。
- 在DDL-X数据集上取得0.89的最高分，领先第二名0.19分。
- 无需任务微调即可生成解释，适合需要透明决策的场景。
现有可解释深度伪造检测方法通常依赖任务定制的多模态大模型，联合完成检测、定位与解释。受智能体使用工具的启发，本文提出感知即工具（Perception-as-Tool）范式，并构建PATE-Forensics：在架构上将检测定位与解释生成解耦，同时在检测定位内部紧密耦合。基于DINOv3的感知工具整合全局、局部块和分割级证据，通过空间化块级与分割级证据生成伪造得分图，指导密集掩码预测。原始图像与工具输出共同构成结构化取证上下文，由通用多模态大模型根据提示约束生成解释，无需任务特定微调。在DDL-X Track 3上，PATE-Forensics取得官方最佳成绩0.89，领先第二名0.19分。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。