In Ictu Oculi: Exposing AI Generated Fake Face Videos by Detecting Eye Blinking
This addresses the challenge of identifying manipulated media for security and verification purposes, though it is an incremental improvement focusing on a specific physiological cue.
The paper tackles the problem of detecting AI-generated fake face videos by identifying the absence of realistic eye blinking, a physiological signal poorly synthesized in deepfake videos, and demonstrates promising performance on DeepFake detection benchmarks.
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 neural networks. 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 tested over benchmarks of eye-blinking detection datasets and also show promising performance on detecting videos generated with DeepFake.