Abstract
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.
Abstract (translated)
面部识别仍然容易受到呈现攻击的影响，因此需要强大的防欺骗解决方案（Face Anti-Spoofing, FAS）。最近基于多模态大型语言模型 (MLLM) 的 FAS 方法将二元分类任务重新表述为生成简短的文本描述，以提高跨域泛化能力。然而，它们的泛化能力仍然有限，因为这些描述主要捕捉直观的语义线索（例如，面具轮廓），而在感知细微视觉模式方面却显得力不从心。为了克服这一限制，我们整合了外部视觉工具到 MLLM 中，鼓励更深入地调查微妙的欺骗线索。 具体而言，我们提出了带有视觉工具增强推理的 FAS (TAR-FAS) 框架，该框架将 FAS 任务重新表述为“带有视觉工具的链式思考”（CoT-VT）模式。这使 MLLM 可以从直观观察开始，并根据需要灵活调用外部视觉工具进行细微级别的调查。为此，我们设计了一种增强工具的数据注释流水线并构建了 ToolFAS-16K 数据集，该数据集中包含了多轮次的工具使用推理轨迹。 此外，我们还引入了一个考虑工具的 FAS 训练流水线，在这个过程中，多样化的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方法。在具有挑战性的十一种跨域协议下进行的大量实验表明，TAR-FAS 达到了最先进的性能，并提供了细粒度的视觉调查，从而为值得信赖的欺骗检测提供支持。
URL
https://arxiv.org/abs/2603.01038
