Blog

The latest from Google Research

Contributing Data to Deepfake Detection Research

Tuesday, September 24, 2019

Posted by Nick Dufour, Google Research and Andrew Gully, Jigsawmore accessible through text-to-speechgenerate training data for medical imagingdeepfakesAI Principlesdataset of synthetic speechinternational challengeJigsawFaceForensics benchmarkProf. Matthias NiessnerProf. Luisa VerdolivaFaceForensics teamYou can download the data on the FaceForensics github page.

A sample of videos from Google’s contribution to the FaceForensics benchmark. To generate these, pairs of actors were selected randomly and deep neural networks swapped the face of one actor onto the head of another.

Actors were filmed in a variety of scenes. Some of these actors are pictured here (top) with an example deepfake (bottom), which can be a subtle or drastic change, depending on the other actor used to create them.

AcknowledgementsSpecial thanks to all our team members and collaborators who work on this project with us: Daisy Stanton, Per Karlsson, Alexey Vorobyov, Thomas Leung, Jeremiah "Spudde" Childs, Avneesh Sud, Christoph Bregler, Andreas Roessler, Davide Cozzolino, Justus Thies, Luisa Verdoliva, Matthias Niessner, and the hard-working actors and film crew who helped make this dataset possible.