How DeepFakes Work?
As discussed above, Deepfakes replicate the data of faces and expressions which cannot be easily identified by a human eye. Whereas, GAN produces data that learns from deep learning and uses generators and discriminators.
Today there are apps like DeepFaceLab that learn by themselves from the provided inputs along with the facial expressions layer by layer and accordingly manipulate the data. In short, it can also be considered as a video editor tool that can be masked with the original video and replace the desired faces.
Although it will take some more time for accuracy it is heavily being used in movies and entertainment industries. Besides this, marketers are also trying to experiment with different promotional content without hiring any models/actors. You may also find some minor project apps that are based on Deepfakes technology which can be used to swap faces and do create some funny videos.
What Are DeepFakes And How Dangerous Are They?
Did you hate the last season of Game of Thrones? Most probably! Did you also watch the online video of Jon Snow saying sorry for the horrible script of season 8? That video obviously wasn’t a real video as Jon Snow knows nothing! It was actually a fake but it looked so real. That’s because it was a DeepFake video made using Artificial Intelligence. Are you wondering what DeepFake is? Let’s check it out! DeepFake uses Deep Learning, a subset of Machine Learning, to create videos that look real but are actually fake. It is basically a technology that can replace the face of a person in an image or a video with so much precision that it looks real. Or it can make a person say something on a video that they never actually said in real life. “What you see is what you get” is no longer true on the internet because of DeepFakes. And that is how you can see Jon Snow blaming the last season of Game of Thrones when this never actually happened!