Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images

TL;DR

This paper introduces a novel method for face anti-spoofing that leverages vision-language models to generate and optimize spoof prompts, significantly improving generalization to unseen attack types using only real face images from a single domain.

Contribution

It proposes a diverse spoof prompt optimization framework that learns effective prompts for unknown spoof attacks without using spoof images, enhancing cross-domain generalization in face anti-spoofing.

Findings

Achieves state-of-the-art generalization across nine datasets.

Effectively transfers knowledge from vision-language models.

No spoof face images needed for training.

Abstract

Face anti-spoofing is a critical technology for ensuring the security of face recognition systems. However, its ability to generalize across diverse scenarios remains a significant challenge. In this paper, we attribute the limited generalization ability to two key factors: covariate shift, which arises from external data collection variations, and semantic shift, which results from substantial differences in emerging attack types. To address both challenges, we propose a novel approach for learning unknown spoof prompts, relying solely on real face images from a single source domain. Our method generates textual prompts for real faces and potential unknown spoof attacks by leveraging the general knowledge embedded in vision-language models, thereby enhancing the model's ability to generalize to unseen target domains. Specifically, we introduce a diverse spoof prompt optimization framework to learn effective prompts. This framework constrains unknown spoof prompts within a relaxed prior knowledge space while maximizing their distance from real face images. Moreover, it enforces semantic independence among different spoof prompts to capture a broad range of spoof patterns. Experimental results on nine datasets demonstrate that the learned prompts effectively transfer the knowledge of vision-language models, enabling state-of-the-art generalization ability against diverse unknown attack types across unseen target domains without using any spoof face images.