Face Anti-spoofing based on Contour-constrained Anomaly Detection

Face recognition systems are increasingly susceptible to spoofing attacks, which pose serious security risks in biometric authentication. Traditional face anti-spoofing is typically framed as a binary classification problem, but the diversity and evolving nature of spoofing techniques hinder generalization. To address this, we reformulate face anti-spoofing as an anomaly detection task, training o…