mlsanityData to 7 Oct 2026

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

arXiv 2607.26432 ↗First posted 29 Jul 2026cs.CV cs.AIcited by 0

On the map: LLM reasoning → Multimodal reasoning

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

19 of 49 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning22 Nov
  2. 2025Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing2 Jun
  3. 2024SHIELD : An Evaluation Benchmark for Face Spoofing and Forgery Detection with Multimodal Large Language Models6 Feb
  4. 2023Lenna: Language Enhanced Reasoning Detection Assistant5 Dec

Other references · 15

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2025Qwen2.5-VL Technical Reportcited by 5,418
  3. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,689
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  5. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  6. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  7. 2025Group Sequence Policy Optimizationcited by 788
  8. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 283
  9. 2024Efficient Multimodal Learning from Data-centric Perspectivecited by 120
  10. 2022Multi-domain Learning for Updating Face Anti-spoofing Modelscited by 39
  11. 2024Gradient Alignment for Cross-Domain Face Anti-Spoofingcited by 26
  12. 2024Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesiscited by 16
3 more
  1. 2025FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Modelscited by 6
  2. 2023TeG-DG: Textually Guided Domain Generalization for Face Anti-Spoofingcited by 2
  3. 2025Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
  2. 2026Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing
  3. 2026MS-MFAD : Multimodal large language models for Face Anti-spoofing Detection
  4. 2025Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models
  5. 2025SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining
  6. 2026UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
  7. 2023FLIP: Cross-domain Face Anti-spoofing with Language Guidance
  8. 2025InstructFLIP: Exploring Unified Vision-Language Model for Face Anti-spoofing