# DRL-FAS: A Novel Framework Based on Deep Reinforcement Learning for Face Anti-Spoofing

arXiv: https://arxiv.org/abs/2009.07529 · HTML: https://mlsanity.com/paper/2009.07529/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 25 of 25)

- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [Deep Learning for Face Anti-Spoofing: A Survey](https://mlsanity.com/paper/2106.14948/) (2021)
- [Beyond the Prior Forgery Knowledge: Mining Critical Clues for General Face Forgery Detection](https://mlsanity.com/paper/2304.12489/) (2023)
- [Meta-Teacher For Face Anti-Spoofing](https://mlsanity.com/paper/2111.06638/) (2021)
- [Learning Meta Pattern for Face Anti-Spoofing](https://mlsanity.com/paper/2110.06753/) (2021)
- [Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cues](https://mlsanity.com/paper/2208.05401/) (2022)
- [Flexible-Modal Face Anti-Spoofing: A Benchmark](https://mlsanity.com/paper/2202.08192/) (2022)
- [Dual Spoof Disentanglement Generation for Face Anti-spoofing with Depth Uncertainty Learning](https://mlsanity.com/paper/2112.00568/) (2021)
- [Reinforcement Learning for Feedback-Enabled Cyber Resilience](https://mlsanity.com/paper/2107.00783/) (2021)
- [Digital and Physical Face Attacks: Reviewing and One Step Further](https://mlsanity.com/paper/2209.14692/) (2022)
- [Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation](https://mlsanity.com/paper/2303.00917/) (2023)
- [Towards Data-Centric Face Anti-Spoofing: Improving Cross-domain Generalization via Physics-based Data Synthesis](https://mlsanity.com/paper/2409.03501/) (2024)
- [One-Class Knowledge Distillation for Face Presentation Attack Detection](https://mlsanity.com/paper/2205.03792/) (2022)
- [S-Adapter: Generalizing Vision Transformer for Face Anti-Spoofing with Statistical Tokens](https://mlsanity.com/paper/2309.04038/) (2023)
- [Few-Shot Domain Expansion for Face Anti-Spoofing](https://mlsanity.com/paper/2106.14162/) (2021)
- [Domain Generalization for Face Anti-spoofing via Content-aware Composite Prompt Engineering](https://mlsanity.com/paper/2504.04470/) (2025)
- [Myope Models -- Are face presentation attack detection models short-sighted?](https://mlsanity.com/paper/2111.11127/) (2021)
- [Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning](https://mlsanity.com/paper/2505.13327/) (2025)
- [Asymmetric Modality Translation For Face Presentation Attack Detection](https://mlsanity.com/paper/2110.09108/) (2021)
- [Wild Face Anti-Spoofing Challenge 2023: Benchmark and Results](https://mlsanity.com/paper/2304.05753/) (2023)
- [Race Bias Analysis of Bona Fide Errors in face anti-spoofing](https://mlsanity.com/paper/2210.05366/) (2022)
- [IFAST: Weakly Supervised Interpretable Face Anti-spoofing from Single-shot Binocular NIR Images](https://mlsanity.com/paper/2309.17399/) (2023)
- [Forensicability Assessment of Questioned Images in Recapturing Detection](https://mlsanity.com/paper/2209.01935/) (2022)
- [Face Presentation Attack Detection](https://mlsanity.com/paper/2212.03680/) (2022)
- [Time-Aware Face Anti-Spoofing with Rotation Invariant Local Binary Patterns and Deep Learning](https://mlsanity.com/paper/2408.14829/) (2024)

## Abstract (arXiv)

Inspired by the philosophy employed by human beings to determine whether a presented face example is genuine or not, i.e., to glance at the example globally first and then carefully observe the local regions to gain more discriminative information, for the face anti-spoofing problem, we propose a novel framework based on the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN). In particular, we model the behavior of exploring face-spoofing-related information from image sub-patches by leveraging deep reinforcement learning. We further introduce a recurrent mechanism to learn representations of local information sequentially from the explored sub-patches with an RNN. Finally, for the classification purpose, we fuse the local information with the global one, which can be learned from the original input image through a CNN. Moreover, we conduct extensive experiments, including ablation study and visualization analysis, to evaluate our proposed framework on various public databases. The experiment results show that our method can generally achieve state-of-the-art performance among all scenarios, demonstrating its effectiveness.