AI-generated faces have enriched human life, such as entertainment,
education, and art. However, they also pose misuse risks. Therefore, detecting
AI-generated faces becomes crucial, yet current detectors show biased
performance across different demographic groups. Mitigating biases can be done
by designing algorithmic fairness methods, which usually require
demographically annotated face datasets for model training. However, no
existing dataset comprehensively encompasses both demographic attributes and
diverse generative methods, which hinders the development of fair detectors for
AI-generated faces. In this work, we introduce the AI-Face dataset, the first
million-scale demographically annotated AI-generated face image dataset,
including real faces, faces from deepfake videos, and faces generated by
Generative Adversarial Networks and Diffusion Models. Based on this dataset, we
conduct the first comprehensive fairness benchmark to assess various AI face
detectors and provide valuable insights and findings to promote the future fair
design of AI face detectors. Our AI-Face dataset and benchmark code are
publicly available at this https URL

AI 生成的人脸已经丰富了人类的生活，但也存在滥用风险。为了缓解偏见，设计算法公平方法是关键，然而当前检测器在不同人群中表现出偏见。本研究引入了 AI-Face 数据集，该数据集是首个具备人口属性注释的、包括真实人脸、deepfake 视频中的人脸以及由生成对抗网络和扩散模型生成的人脸的百万级 AI 生成人脸图像数据集。基于该数据集，我们进行了首次全面的公平性评估，评估了各种 AI 人脸检测器，并提供有价值的见解和发现，以推动未来公平设计 AI 人脸检测器。我们的 AI-Face 数据集和评估代码在此 https URL 上公开可用。