Multimodal Approach for DeepFake Detection
Michael Lomnitz, Z. Hampel-Arias, Vishal Sandesara, Simon Hu
Abstract
Generative Adversarial Networks (GANs) have become increasingly popular in machine learning because of their ability to mimic any distribution of data. Though GANs can be leveraged for legitimate purposes, they have increasingly been used to create manipulative and misleading synthetic media, known as deepfakes, intended for nefarious purposes. In this submission we discuss a multimodal deepfake detection solution submitted against the Facebook DeepFake Detection Challenge, a state of the art benchmark dataset and competition released at the end of 2019. Our solution incorporates information from single images and series of images, and also incorporates temporal information from audio and video data, and was ultimately ranked among the top 25% of teams.