# SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining

arXiv: https://arxiv.org/abs/2503.19982 · HTML: https://mlsanity.com/paper/2503.19982/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 33 references that are in the map.
- First posted on arXiv 25 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Searching Central Difference Convolutional Networks for Face Anti-Spoofing](https://mlsanity.com/paper/2003.04092/) (2020)
- [Cross-domain Face Presentation Attack Detection via Multi-domain Disentangled Representation Learning](https://mlsanity.com/paper/2004.01959/) (2020)
- [Deep Spatial Gradient and Temporal Depth Learning for Face Anti-spoofing](https://mlsanity.com/paper/2003.08061/) (2020)
- [Dual-Cross Central Difference Network for Face Anti-Spoofing](https://mlsanity.com/paper/2105.01290/) (2021)
- [FLIP: Cross-domain Face Anti-spoofing with Language Guidance](https://mlsanity.com/paper/2309.16649/) (2023)
- [Detection and Continual Learning of Novel Face Presentation Attacks](https://mlsanity.com/paper/2108.12081/) (2021)
- [Benchmarking Joint Face Spoofing and Forgery Detection with Visual and Physiological Cues](https://mlsanity.com/paper/2208.05401/) (2022)
- [Anomaly Detection-Based Unknown Face Presentation Attack Detection](https://mlsanity.com/paper/2007.05856/) (2020)
- [Camera Invariant Feature Learning for Generalized Face Anti-spoofing](https://mlsanity.com/paper/2101.10075/) (2021)

## Built on by (most cited first, 5 of 5)

- [Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images](https://mlsanity.com/paper/2505.03611/) (2025)
- [Exploring Task-Solving Paradigm for Generalized Cross-Domain Face Anti-Spoofing via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.21895/) (2025)
- [Multi-Modal Face Anti-Spoofing via Cross-Modal Feature Transitions](https://mlsanity.com/paper/2507.05575/) (2025)
- [Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation](https://mlsanity.com/paper/2509.23475/) (2025)
- [Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing](https://mlsanity.com/paper/2608.17351/) (2026)

## Abstract (arXiv)

Face anti-spoofing (FAS) plays a pivotal role in ensuring the security and reliability of face recognition systems. With advancements in vision-language pretrained (VLP) models, recent two-class FAS techniques have leveraged the advantages of using VLP guidance, while this potential remains unexplored in one-class FAS methods. The one-class FAS focuses on learning intrinsic liveness features solely from live training images to differentiate between live and spoof faces. However, the lack of spoof training data can lead one-class FAS models to inadvertently incorporate domain information irrelevant to the live/spoof distinction (e.g., facial content), causing performance degradation when tested with a new application domain. To address this issue, we propose a novel framework called Spoof-aware one-class face anti-spoofing with Language Image Pretraining (SLIP). Given that live faces should ideally not be obscured by any spoof-attack-related objects (e.g., paper, or masks) and are assumed to yield zero spoof cue maps, we first propose an effective language-guided spoof cue map estimation to enhance one-class FAS models by simulating whether the underlying faces are covered by attack-related objects and generating corresponding nonzero spoof cue maps. Next, we introduce a novel prompt-driven liveness feature disentanglement to alleviate live/spoof-irrelative domain variations by disentangling live/spoof-relevant and domain-dependent information. Finally, we design an effective augmentation strategy by fusing latent features from live images and spoof prompts to generate spoof-like image features and thus diversify latent spoof features to facilitate the learning of one-class FAS. Our extensive experiments and ablation studies support that SLIP consistently outperforms previous one-class FAS methods.