# Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing

arXiv: https://arxiv.org/abs/2608.17351 · HTML: https://mlsanity.com/paper/2608.17351/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 71 references that are in the map.
- First posted on arXiv 18 Aug 2026.

## Builds on (most cited first, 30 of 35)

- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Learning to Diversify for Single Domain Generalization](https://mlsanity.com/paper/2108.11726/) (2021)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Progressive Domain Expansion Network for Single Domain Generalization](https://mlsanity.com/paper/2103.16050/) (2021)
- [Learn Convolutional Neural Network for Face Anti-Spoofing](https://mlsanity.com/paper/1408.5601/) (2014)
- [Deep Tree Learning for Zero-shot Face Anti-Spoofing](https://mlsanity.com/paper/1904.02860/) (2019)
- [PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition](https://mlsanity.com/paper/2203.14325/) (2022)
- [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)
- [On Disentangling Spoof Trace for Generic Face Anti-Spoofing](https://mlsanity.com/paper/2007.09273/) (2020)
- [CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing](https://mlsanity.com/paper/1908.10654/) (2019)
- [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)
- [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)
- [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)
- [Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models](https://mlsanity.com/paper/2501.01720/) (2025)
- [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)
- [FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models](https://mlsanity.com/paper/2505.09415/) (2025)
- [SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining](https://mlsanity.com/paper/2503.19982/) (2025)
- [Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing](https://mlsanity.com/paper/2503.22984/) (2025)
- [Harnessing Chain-of-Thought Reasoning in Multimodal Large Language Models for Face Anti-Spoofing](https://mlsanity.com/paper/2506.01783/) (2025)
- [Hyp-OC: Hyperbolic One Class Classification for Face Anti-Spoofing](https://mlsanity.com/paper/2404.14406/) (2024)
- [PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning](https://mlsanity.com/paper/2511.17927/) (2025)
- [Learning Knowledge-based Prompts for Robust 3D Mask Presentation Attack Detection](https://mlsanity.com/paper/2505.03610/) (2025)
- [Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing](https://mlsanity.com/paper/2401.01102/) (2024)

## Abstract (arXiv)

Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target domains contain diverse attack types absent from training. Existing prompt-based approaches often express spoofing through category semantics or language guidance, which is effective for modeling high-level concepts but is less suited to explicitly capturing the evolving fine-grained and spatially heterogeneous forensic evidence of unseen attacks. Motivated by the hypothesis that many unseen attacks can be characterized by new combinations of recurring visual cues, we propose a compositional forensic visual prompt learning framework that operates entirely in the visual feature space. Built on a frozen ViT-based vision foundation model, the framework employs patch-aware attention to refine a shared set of learnable micro-forensic primitives into localized forensic evidence units derived from image patches. Class-specific global contextual prompts then provide input-dependent routing weights that adaptively select and compose these primitives into compositional forensic visual prompts for real/spoof discrimination. The primitives are not assigned predefined semantic meanings; instead, their specialization and reuse emerge from shared parameterization and joint optimization across categories. Extensive experiments on nine open-world protocols demonstrate state-of-the-art performance, strong cross-domain generalization, and robust adaptation to unseen attacks.