Deepfakes are manipulated image, audio or video documents in which products, people and actions have been deliberately inserted into the documents with artificial intelligence
. In the documents, the contents are falsified in order to circulate misrepresentations and discredit well-known personalities. Deepfakes are falsifications of images and sound. In the photos and video
, faces and even whole persons are exchanged and imitated in the course of movement. While the exchange of faces in photos, the face swapping, is still simple, videos in which the body posture, the movement dynamics, the body puppetry, or the speech and accent adaptation, the voice swapping, are much more complicated and computationally intensive. Hence the use of artificial intelligence.To perform the computationally intensive deepfake operations, one works with two artificial neural networks, Generative Adversarial Networks (GAN). The two networks work together, one forming a generator, the other a discriminator
. The generator is a learning component whose results are generated according to a certain distribution. In contrast, the discriminator analyzes the results against the given distribution. Deviations are adjusted by the discriminator, and through the learning algorithm, the results presented are constantly improving.