AI RESEARCH
UniShield: Unified Face Attack Detection via KG-Informed Multimodal Reasoning
arXiv CS.CV
•
ArXi:2605.08709v1 Announce Type: new Unified face attack detection (UAD) requires recognizing physical spoofing and digital forgery within a shared decision space, yet existing discriminative or prompt-based methods largely rely on appearance correlations and provide limited evidence-grounded reasoning. We propose UniShield, a knowledge-grounded multimodal reasoning framework for unified face attack defense.