Smashing Security cover image

Deepfake dangers, AI image opt out, and controlling your urges

Smashing Security

00:00

How Deep Fakes Are Created

Many deep fakes use generative adversarial networksk or gans. One machine learning model trains on a data set and then creates a video forgery, while the other attempts to detect it. And with this process, he says, at the foundation of deep fakes, neither pattern recognition techniques nor humans will be able to reliably recognize them.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app