Challenges and Solutions in DeepFakes

TL;DR

This paper discusses the challenges posed by DeepFake technology and introduces a large dataset of real and fake faces to train models for detecting manipulated images and videos.

Contribution

It presents a new dataset of 140,000 faces, combining real and fake images, to improve DeepFake detection methods.

Findings

The dataset includes 70k real faces from Flickr and 70k fake faces generated by StyleGAN.

Models trained on this dataset can distinguish real from fake faces.

The dataset aims to advance research in DeepFake detection techniques.

Abstract

Deep learning has been successfully appertained to solve various complex problems in the area of big data analytics to computer vision. A deep learning-powered application recently emerged is Deep Fake. It helps to create fake images and videos that human cannot distinguish them from the real ones and are recent off-shelf manipulation technique that allows swapping two identities in a single video. Technology is a controversial technology with many wide-reaching issues impacting society. So, to counter this emerging problem, we introduce a dataset of 140k real and fake faces which contain 70k real faces from the Flickr dataset collected by Nvidia, as well as 70k fake faces sampled from 1 million fake faces generated by style GAN. We will train our model in the dataset so that our model can identify real or fake faces.