With the rapid development of computer hardware and machine learning algorithms, fake images and videos, such as face images generated by DeepFake, have become much easier to be generated yet much harder to be distinguished. As a result, the research of fake face detection has draw a lot of attention. Many of the detection methods are based on traditional research in biometric anti-spoofing and modern data-driven deep learning algorithms. The growing interests in fake face detection have resulted in a increasing number of workshops in top computer vision conferences and competitions such as the recent MFC2018 and DFDC launched by NIST and Facebook, respectively.