A GAN-Based Model of Deepfake Detection in Social Media

Abstract

DeepFake uses Generative + Adversarial Network for successfully switching the identities of two people. Large public databases and deep learning methods are now rapidly available because of the proliferation of easily accessible tools online. It has resulted in the emergence of very real appealing fake content that produced a bad impact and challenges for society to deal. Pre-trained generative adversarial networks (GANs) that can flawlessly substitute one person's face in a video or image for that other are proving supportive for implementing deepfake. This paper primarily presented a study of methods used to implement deepfake. Also, discuss the main deepfake's manipulation and detection techniques, and the implementation and detection of deepfake using Deep Convolution-based GAN models. A study of Comparative analyses of proposed GAN with other exiting GAN models using parameters Inception Score “IS” and Fréchet Inception Distance “FID” is also embedded. Along with the abovementioned, the paper discusses open issues and future trends that should be considered to advance in the field.