Apple Granted Patent for Deepfakes Based on Reference Images
upstart writes:
Apple Granted Patent for Deepfakes Based on Reference Images:
Remember how entire governments have been pressing tech companies to tackle the deepfakes permeating their online platforms? Well, they have even more work cut out for themselves now. On Tuesday the US Patent Office granted Apple a patent for "face image generation with pose and expression control"-AKA deepfakes-based on reference images.
According to patent documents first spotted by Patently Apple, Apple's technology uses machine learning to create synthetic images of human faces based on a reference image provided by the user. Once the tech has generated a synthetic face, it can manipulate that face to create changes in expression. Given a reference image or "target shape" depicting a whole person (not just a face), the image generator can also create synthetic images in which the reference person is posed differently.
The generator's neural network is trained to constrain generation enough that the synthetic image can convincingly look like the reference person, not an entirely new-or simply "inspired-creation. These constraints are incorporated using a generative adversarial network (GAN) in which multiple synthetic images are generated, after which a discriminator attempts to determine which images are real or synthetic. The discriminator's findings are then used to further train both the generator and the discriminator.
[...] Others think Apple could be working towards an app or feature that puts a "fun" or "convenient" twist on deepfakes. If that ends up happening, at which point does the [...] proposed AI Bill of Rights get involved?
Read more of this story at SoylentNews.