Domain-generalizable Face Anti-Spoofing with Patch-based Multi-tasking and Artifact Pattern Conversion

2026-03-01

Pattern Recognition

AI Summary

This work addresses the limited generalization of existing face presentation attack detection methods to unseen domains and novel attack types, primarily due to insufficient diversity in training data. To overcome this challenge, the authors propose Pattern Conversion GAN (PCGAN), which disentangles identity-related features from spoofing artifacts in the latent space and incorporates a patch-level multi-task learning mechanism to synthesize diverse spoofing samples, thereby enhancing model robustness. By innovatively integrating artifact pattern transformation with feature disentanglement, PCGAN significantly improves detection performance against both unknown-domain attacks and localized presentation attacks across multiple benchmark datasets, effectively strengthening the security of face recognition systems.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Adversarial Learning & Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data
• Security and Privacy: Large-scale security measurements

Abstract

Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing their ability to handle unseen visual domains and spoofing methods. We introduce the Pattern Conversion Generative Adversarial Network (PCGAN) to enhance domain generalization in FAS. PCGAN effectively disentangles latent vectors for spoof artifacts and facial features, allowing to generate images with diverse artifacts. We further incorporate patch-based and multi-task learning to tackle partial attacks and overfitting issues to facial features. Our extensive experiments validate PCGAN's effectiveness in domain generalization and detecting partial attacks, giving a substantial improvement in facial recognition security.

Problem

• Face Anti-Spoofing
• domain generalization
• spoofing attacks
• dataset diversity
• partial attacks

Innovation

• Domain Generalization
• Face Anti-Spoofing
• Generative Adversarial Network
• Patch-based Learning
• Multi-task Learning