HOW ARE FAKE FACES CREATED?

Understand the algorithm behind AI INVADERS AND AI DEFENDERS

AI INVADER

Allows users to create AI-Generated faces based on real images by modifying 4 different parameters.

AI DEFENDER

Challenges users to distinguish fake faces from real faces.

Random noise

Newly generated faces passing onto the game

Real photos

In a GANs Model,

GENERATOR

AI INVADER acts like a generator, which generates new content, and AI DEFENDER acts like a descriminator. New content is constently passing onto the discriminator along with real training data (ground truth) to be assessed.

DISCRIMINATOR

In a GANs Model,

AI INVADER acts like a generator, which generates new content, and AI DEFENDER acts like a descriminator. New content is constently passing onto the discriminator along with real training data (ground truth) to be assessed.

GANs Algorithm

Here are the steps a GAN takes:

  • The generator takes in random numbers and returns an image.
  • This generated image is fed into the discriminator alongside a stream of images taken from the actual, ground-truth dataset.
  • The discriminator takes in both real and fake images and returns probabilities, a number between 0 and 1, with 1 representing a prediction of authenticity and 0 representing fake.

    • Here are the steps a GAN takes:

  • The generator takes in random numbers and returns an image.
  • This generated image is fed into the discriminator alongside a stream of images taken from the actual, ground-truth dataset.
  • The discriminator takes in both real and fake images and returns probabilities, a number between 0 and 1, with 1 representing a prediction of authenticity and 0 representing fake.