Deepfakes are a type of synthetic media where a person’s image or video is swapped with another person’s likeness. This is achieved through deep learning techniques, hence the name “deepfakes”, which is a portmanteau of “deep learning” and “fake”.
Deepfakes involve the manipulation of facial appearance through deep generative methods. They leverage powerful techniques from machine learning and artificial intelligence to manipulate or generate visual and audio content that can convincingly deceive. The main machine learning methods used to create deepfakes are based on deep learning and involve training generative neural network architectures.
While the act of creating fake content is not new, deepfakes have garnered widespread attention for their potential use in creating misleading videos, fake news, hoaxes, and financial fraud. This has elicited responses from both industry and government to detect and limit their use.