Visible to the public Exposing Deep Fakes Using Inconsistent Head Poses

TitleExposing Deep Fakes Using Inconsistent Head Poses
Publication TypeConference Paper
Year of Publication2019
AuthorsYang, X., Li, Y., Lyu, S.
Conference NameICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Date Publishedmay
Keywords3D head poses, AI-generated fake face images, Cameras, classification method, Deep Fakes, DeepFake, deepfake detection, Face, face recognition, feature extraction, Head Pose Estimation, Human Behavior, human factors, image classification, inconsistent head poses, Media Forensics, Metrics, Neural networks, pose estimation, pubcrawl, resilience, Resiliency, Scalability, stereo image processing, Support vector machines, SVM classifier, synthesized face region splicing, Three-dimensional displays, Videos
AbstractIn this paper, we propose a new method to expose AI-generated fake face images or videos (commonly known as the Deep Fakes). Our method is based on the observations that Deep Fakes are created by splicing synthesized face region into the original image, and in doing so, introducing errors that can be revealed when 3D head poses are estimated from the face images. We perform experiments to demonstrate this phenomenon and further develop a classification method based on this cue. Using features based on this cue, an SVM classifier is evaluated using a set of real face images and Deep Fakes.
Citation Keyyang_exposing_2019