从直觉到探究:面向可泛化人脸反欺骗的工具增强推理多模态大模型框架
From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
把外部视觉工具(如放大、局部裁剪等细粒度分析算子)接入 MLLM 的推理链,并用 GRPO 类强化学习让模型自主决定何时调用工具,这一「工具增强思维链」范式可直接迁移到需要细粒度视觉证据的检测/鉴伪任务。
原文依据 reformulates the FAS task as a Chain-of-Thought with Visual Tools (CoT-VT) paradigm
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人脸识别仍然容易受到呈现攻击的威胁,因此需要鲁棒的人脸反欺骗(FAS)方案。近期基于多模态大模型(MLLM)的 FAS 方法将二分类任务重新表述为生成简短文本描述,以提升跨域泛化能力。然而,这类描述的泛化性仍然有限,因为它们主要捕捉直觉性的语义线索(例如掩码轮廓),而难以感知细粒度的视觉模式。为解决这一局限,我们将外部视觉工具引入 MLLM,以鼓励对细微欺骗线索进行更深入的探究。具体而言,我们提出工具增强推理 FAS(TAR-FAS)框架,将 FAS 任务重新表述为带视觉工具的思维链(CoT-VT)范式,使 MLLM 能够从直觉观察出发,并自适应地调用外部视觉工具进行细粒度探究。为此,我们设计了工具增强的数据标注流程,并构建了 ToolFAS-16K 数据集,其中包含多轮工具使用推理轨迹。此外,我们引入了工具感知的 FAS 训练流程,其中多样化工具组相对策略优化(DT-GRPO)使模型能够自主学习高效的工具使用。在具有挑战性的一对十一跨域协议下进行的大量实验表明,TAR-FAS 取得了 SOTA 性能,同时为可信的欺骗检测提供了细粒度的视觉探究。
英文原文摘要 1459 字符
Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FAS) solutions. Recent MLLM-based FAS methods reformulate the binary classification task as the generation of brief textual descriptions to improve cross-domain generalization. However, their generalizability is still limited, as such descriptions mainly capture intuitive semantic cues (e.g., mask contours) while struggling to perceive fine-grained visual patterns. To address this limitation, we incorporate external visual tools into MLLMs to encourage deeper investigation of subtle spoof clues. Specifically, we propose the Tool-Augmented Reasoning FAS (TAR-FAS) framework, which reformulates the FAS task as a Chain-of-Thought with Visual Tools (CoT-VT) paradigm, allowing MLLMs to begin with intuitive observations and adaptively invoke external visual tools for fine-grained investigation. To this end, we design a tool-augmented data annotation pipeline and construct the ToolFAS-16K dataset, which contains multi-turn tool-use reasoning trajectories. Furthermore, we introduce a tool-aware FAS training pipeline, where Diverse-Tool Group Relative Policy Optimization (DT-GRPO) enables the model to autonomously learn efficient tool use. Extensive experiments under a challenging one-to-eleven cross-domain protocol demonstrate that TAR-FAS achieves SOTA performance while providing fine-grained visual investigation for trustworthy spoof detection.