# Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning

arXiv: https://arxiv.org/abs/2506.21895 · HTML: https://mlsanity.com/paper/2506.21895/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 33 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Learn Convolutional Neural Network for Face Anti-Spoofing](https://mlsanity.com/paper/1408.5601/) (2014)
- [CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing](https://mlsanity.com/paper/2003.05136/) (2020)
- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing](https://mlsanity.com/paper/1812.00408/) (2018)
- [FLIP: Cross-domain Face Anti-spoofing with Language Guidance](https://mlsanity.com/paper/2309.16649/) (2023)
- [Multi-domain Learning for Updating Face Anti-spoofing Models](https://mlsanity.com/paper/2208.11148/) (2022)
- [Deep Models and Shortwave Infrared Information to Detect Face Presentation Attacks](https://mlsanity.com/paper/2007.11469/) (2020)
- [Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis](https://mlsanity.com/paper/2409.03501/) (2024)
- [DiffFAS: Face Anti-Spoofing via Generative Diffusion Models](https://mlsanity.com/paper/2409.08572/) (2024)
- [Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering](https://mlsanity.com/paper/2504.04470/) (2025)
- [Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant Factors](https://mlsanity.com/paper/2407.08243/) (2024)
- [SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining](https://mlsanity.com/paper/2503.19982/) (2025)

## Built on by (most cited first, 1 of 1)

- [FAS-R1: A Unified Multi-Task MLLM for Reasoning Face Anti-Spoofing](https://mlsanity.com/paper/2607.26432/) (2026)

## Abstract (arXiv)

Recently the emergence of novel presentation attacks has drawn increasing attention to face anti-spoofing. However, existing methods tend to memorize data patterns from the training set, resulting in poor generalization to unknown attack types across different scenarios and limited interpretability. To address these challenges, this paper presents a reinforcement fine-tuning-based face anti-spoofing method that stimulates the capabilities of multimodal large language models to think and learn how to solve the anti-spoofing task itself, rather than relying on the memorization of authenticity patterns. We design verifiable class consistent reward and reasoning consistent reward, and employ a GRPO-based optimization strategy to guide the model in exploring reasoning policies from multiple perspectives to maximize expected rewards. As a result, through iterative trial-and-error learning while retaining only high-reward trajectories, the model distills highly generalizable decision-making rules from the extensive solution space to effectively address cross-domain face anti-spoofing tasks. Extensive experimental results demonstrate that our method achieves state-of-the-art cross-domain generalization performance. It generalizes well to diverse unknown attack types in unseen target domains while providing interpretable reasoning for its authenticity decisions without requiring labor-intensive textual annotations for training.