Year: 2018
Type: conference-paper
Abstract: The new developments in deep generative networks have significantly improve the quality and efficiency in generating realistically-looking fake face videos. In this work, we describe a new method to expose fake face videos generated with deep neural network models. Our method is based on detection of eye blinking in the videos, which is a physiological signal that is not well presented in the synthesized fake videos. Our method is evaluated over benchmarks of eye-blinking detection datasets and shows promising performance on detecting videos generated with DNN based software DeepFake.
Authors: Yuezun Li, Ming-Ching Chang, Siwei Lyu
Institution: University at Albany, State University of New York
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2914447220
