These Incredibly Realistic Fake Faces Show How AI Can Now Mess With Us
This starts to be more than a bit concerning. The faces in this post look like pretty normal humans. They could be social media shots. However, they were generated by a recent type of algorithm: generative adversarial network, or GAN.
Nvidia researchers Tero Karras, Samuli Laine, and Timo Aila posted details of the method to produce completely imaginary fake faces with stunning, almost eerie, realism.
GANs employ two "dueling" neural networks to train a model to learn the nature of a dataset well enough to generate convincing fakes. When you apply GANs to images, this provides a way to generate often highly realistic still fakes you could use for extremely hard to detect social engineering attacks, especially combined with deep fake videos.
Here is the blog post with the links to the paper, still shots and example videos. Check it out and shiver:
Warm regards, Stu