# FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing

arXiv: https://arxiv.org/abs/2607.26432 · HTML: https://mlsanity.com/paper/2607.26432/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models](https://mlsanity.com/paper/2311.07575/) (2023)
- [Efficient Multimodal Learning from Data-centric Perspective](https://mlsanity.com/paper/2402.11530/) (2024)
- [SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models](https://mlsanity.com/paper/2402.04178/) (2024)
- [Multi-domain Learning for Updating Face Anti-spoofing Models](https://mlsanity.com/paper/2208.11148/) (2022)
- [Lenna: Language Enhanced Reasoning Detection Assistant](https://mlsanity.com/paper/2312.02433/) (2023)
- [Gradient Alignment for Cross-Domain Face Anti-Spoofing](https://mlsanity.com/paper/2402.18817/) (2024)
- [Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis](https://mlsanity.com/paper/2409.03501/) (2024)
- [FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models](https://mlsanity.com/paper/2505.09415/) (2025)
- [Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing](https://mlsanity.com/paper/2506.01783/) (2025)
- [PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning](https://mlsanity.com/paper/2511.17927/) (2025)
- [TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2311.18420/) (2023)
- [Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.21895/) (2025)

## Abstract (arXiv)

Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence for human inspection. Existing discriminative FAS models remain largely label-centric, while recent MLLM-based methods offer structured outputs but still rely mainly on supervised fine-tuning, often producing template-like rationales and weak optimization for difficult attacks. We propose FAS-R1, a two-stage reasoning-oriented MLLM framework for unified FAS prediction, covering authenticity classification, attack-type recognition and spoof-region localization. FAS-R1 first uses FAS-R1-23K, a high-quality long-CoT dataset, for cold-start supervised fine-tuning, and then performs FAS-specific GRPO post-training. Degradation-Simulated Augmentation (DSA) encourages stable spoof-cue reasoning across visual-quality shifts, while Difficulty-Aware GRPO (DA-GRPO) mitigates easy-sample dominance that may leave difficult task--attack groups under-optimized, especially for subtle or ambiguous attacks such as makeup and mask attacks. The main 3B FAS-R1 model achieves 98.75% authenticity accuracy, 93.33% attack-type accuracy, and 96.30/94.73% AP@40/AP@50 in-domain. It also outperforms the compared systems in cross-domain authenticity generalization and answer-and-rationale quality. Experiments with different base models further show favorable scaling behavior. The code will be released soon.