Exposing Deep Fakes Using Inconsistent Head Poses
This addresses the challenge of identifying manipulated media for security and verification purposes, representing an incremental improvement by applying a specific cue to an existing detection problem.
The paper tackles the problem of detecting AI-generated fake face images or videos (Deep Fakes) by exploiting inconsistencies in 3D head poses introduced during synthesis, and it develops an SVM classifier that demonstrates effectiveness in distinguishing real faces from Deep Fakes.
In 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.