Governmental Commission approved a “roadmap” to develop new Internet technologies. Among the expected implementation goals is the fight against deepfakes
Behind each song is a driving video that the developers shoot in their studio using motion capture. The performer performs a series of face, eye and lip movements along with the song. This movement is applied to the model, which is then mapped to images that users submit. Using some “tricky math”, the app processes the uploaded photos and generates videos
The Moscow School of Management SKOLKOVO introduces a holographic image of a professor who can be located anywhere in the world
Today, the industry, including biometrics recognition players, is kicking around the idea of creating synthetic data to get around privacy concerns and bias
Researchers say they have found an efficient way for an AI algorithm like those used in biometrics to judge how confident it is with its decisions
Instead of training networks to give an overall fake/not fake prediction, the MIT researchers found that modified generators cannot accurate model certain areas of a fake image so well that a fake image cannot be discerned
Despite the fact that many biometric systems are equipped with algorithms that can detect an attack on them, this is not enough to treat security lightly
This effect is suggested for detecting deepfakes. At this stage of development, it is very difficult to realistically reproduce the blood flow
Voice fraud cases increased by 350% between 2013 and 2017, according to Pindrop, with one in 638 cases using speech synthesis
Dubbed VoiceGesture, the liveness detection tool designed by the researchers is intended to work on smart devices like smartphones and smart speakers