# DINO-VPT: Hierarchical Visual Prompt Tuning for Joint Physical-Digital Face Anti-Spoofing

arXiv: https://arxiv.org/abs/2607.20900 · HTML: https://mlsanity.com/paper/2607.20900/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 35 references that are in the map.
- First posted on arXiv 23 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [On the Detection of Digital Face Manipulation](https://mlsanity.com/paper/1910.01717/) (2019)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision](https://mlsanity.com/paper/1803.11097/) (2018)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning](https://mlsanity.com/paper/2004.01959/) (2020)
- [Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing](https://mlsanity.com/paper/2203.05340/) (2022)
- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing](https://mlsanity.com/paper/2108.02667/) (2021)
- [Dual Reweighting Domain Generalization for Face Presentation Attack Detection](https://mlsanity.com/paper/2106.16128/) (2021)
- [FLIP: Cross-domain Face Anti-spoofing with Language Guidance](https://mlsanity.com/paper/2309.16649/) (2023)
- [Instance-Aware Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2304.05640/) (2023)
- [CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing](https://mlsanity.com/paper/2403.14333/) (2024)
- [Gradient Alignment for Cross-Domain Face Anti-Spoofing](https://mlsanity.com/paper/2402.18817/) (2024)
- [Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models](https://mlsanity.com/paper/2501.01720/) (2025)
- [Joint Physical-Digital Facial Attack Detection Via Simulating Spoofing Clues](https://mlsanity.com/paper/2404.08450/) (2024)
- [Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack Detection](https://mlsanity.com/paper/2504.00458/) (2025)
- [Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuning](https://mlsanity.com/paper/2505.13327/) (2025)
- [Benchmarking Vision Foundation Models for Domain-Generalizable Face Anti-Spoofing](https://mlsanity.com/paper/2604.19196/) (2026)
- [SUEDE:Shared Unified Experts for Physical-Digital Face Attack Detection Enhancement](https://mlsanity.com/paper/2504.04818/) (2025)

## Abstract (arXiv)

With the increasing diversity of spoofing attacks, there is a growing demand for unified Face Anti-Spoofing (FAS) models capable of detecting both physical and digital threats. While existing Vision-Language Models (VLMs) demonstrate high generalization in this context, they heavily rely on complex multimodal fusion and external text encoders. In this paper, we propose DINO-VPT, a lightweight, vision-only framework leveraging hierarchical visual prompt tuning. By dynamically injecting prompts conditioned on input features via a Prompt Routing Network (PRN), our method effectively disentangles diverse spoofing artifacts without requiring multimodal fusion. Evaluations on the UniAttackData benchmark demonstrate that DINO-VPT achieves higher accuracy than state-of-the-art VLM-based methods. Our results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.