The field of face forgery detection and anti-spoofing is rapidly evolving, with a growing focus on the development of innovative solutions that can effectively counter the increasing threat of deepfakes and other forms of facial manipulation. Recent research has explored the potential of multimodal large language models (MLLMs) and vision-language fusion networks to improve the accuracy and robustness of face forgery detection systems. Additionally, there is a growing interest in the use of knowledge-based prompts and causal graph theory to enhance the generalization ability of face anti-spoofing models. These advances have the potential to significantly improve the security and reliability of face recognition systems. Noteworthy papers in this area include:

• A novel Vision-Language Fusion solution for MLLM-enhanced Face Forgery Detection, which achieves state-of-the-art performance in both cross-dataset and intra-dataset evaluations.
• A knowledge-based prompt learning framework for 3D mask presentation attack detection, which demonstrates strong generalization capability and achieves state-of-the-art detection performance on benchmark datasets.
• A approach for learning unknown spoof prompts for generalized face anti-spoofing using only real face images, which enables state-of-the-art generalization ability against diverse unknown attack types across unseen target domains.