FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2026
FaceShield explores explainable face anti-spoofing with multimodal large language models and introduces a unified framework for classification, reasoning, and attack localization.
Recommended citation: Wang, H., Shi, Y., Tao, Z., Gao, Y., Zhang, L., Lin, X., Feng, J., Yuan, X., Yu, Z., & Cao, X. (2026). FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(12), 9811-9819. https://doi.org/10.1609/aaai.v40i12.37945