DeepFakes: Detecting Forged and Synthetic Media Content Using Machine Learning

View on arXiv ← Back to list

Authors: Sm Zobaed, Md Fazle Rabby, Md Istiaq Hossain, Ekram Hossain, Sazib Hasan, Asif Karim, Khan Md. Hasib

Published: 2021-09-07 05:19:36+00:00

Comment: A preprint version

AI Summary

This study comprehensively reviews the rapidly advancing domain of DeepFake technology, covering both creation and detection techniques. It aims to present challenges, research trends, and future directions to foster the development of more robust approaches capable of combating sophisticated DeepFakes.

Abstract

The rapid advancement in deep learning makes the differentiation of authentic and manipulated facial images and video clips unprecedentedly harder. The underlying technology of manipulating facial appearances through deep generative approaches, enunciated as DeepFake that have emerged recently by promoting a vast number of malicious face manipulation applications. Subsequently, the need of other sort of techniques that can assess the integrity of digital visual content is indisputable to reduce the impact of the creations of DeepFake. A large body of research that are performed on DeepFake creation and detection create a scope of pushing each other beyond the current status. This study presents challenges, research trends, and directions related to DeepFake creation and detection techniques by reviewing the notable research in the DeepFake domain to facilitate the development of more robust approaches that could deal with the more advance DeepFake in the future.

Key findings
The paper reveals ongoing challenges in DeepFake generation, such as low-resolution outputs and limitations in attribute manipulation and video continuity. For detection, it highlights issues with biased evaluation against simple baselines, the need for more challenging datasets, and a lack of comprehensive performance metrics beyond accuracy. It emphasizes the necessity for detectors with advanced generalization, robustness against adversarial attacks, and explainable results.
Approach
This paper provides a structured survey and literature review of existing DeepFake generation and detection methods. It categorizes approaches, discusses datasets, highlights limitations, and identifies future research opportunities to guide further advancements in the field.
Datasets
CASIA-WebFace, CelebA, VGGFace, MS-Celeb-1M, VGGFace2, Flickr-Faces-HQ (FFHQ), DeepFake Detection Challenge (DFDC) Preview Dataset, Celeb-DF, FaceForensics++, UADFV, CIFAR-10, ImageNet, LSUN, CelebA-HQ, Google Billion Word, Swiss Roll, Places2, DTD, LFW, Matterport3D, Cityscapes, CMP Facade, UT Zappos, EmotioNet, RaFD, OF, HWDB1.0, VoxCeleb1, CelebV, WFLW, AFHQ, IJB-C, Figaro, Forensics++, MNIST, USPS, RGBD, NYU, FF++, Celeb-DF, UADFV, DFFD, TIMIT, FaceForensics (FF), CEW.
Model(s)
UNKNOWN
Author countries
USA, Australia, Bangladesh
← Previous
Next →