Article 2 of AI: Explainer and Example series

Deepfakes refer to AI generated audio or visual imitations of another person. Infamous cases include scamming a CEO of over $200,000, imitating famous politicians and creating alarming celebrity face swaps.

Declaration of Independence? Source: Albany University

So how does one begin to create fake images? One approach is to use a GAN, abbreviated for General Adversarial Network and usually consists of two convolutional neural networks (CNNs). If you would like a reminder of CNNs and what they are, feel free to check out the first article.

GANs were first introduced in 2014 by Dr. Ian Goodfellow and his team at the University of Montreal, later making Dr. Goodfellow famous within the AI community. Below you can see how GANs have rapidly developed within a four year time span.

Left: GAN generated faces (Ian Goodfellow et Al 2014). Right: GAN generated faces with mixed styles from original faces A and B (Nvidia 2018).

GANs consist of two primary components, the Generator and Discriminator which we will abbreviate to G & D. The role of G is to generate fake images from random inputs that will fool D, which has the job of determining which images are real, and which are fake outputs from G.

#data-science #deepfakes #ai #explain #data analysis