Deep learning for deepfakes creation and detection: A survey

Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can cause threats to privacy, democracy and national security. One...

Full description

Saved in:
Bibliographic Details
Published in:Computer vision and image understanding Vol. 223; p. 103525
Main Authors: Nguyen, Thanh Thi, Nguyen, Quoc Viet Hung, Nguyen, Dung Tien, Nguyen, Duc Thanh, Huynh-The, Thien, Nahavandi, Saeid, Nguyen, Thanh Tam, Pham, Quoc-Viet, Nguyen, Cuong M.
Format: Journal Article
Language:English
Published: Elsevier Inc 01.10.2022
Subjects:
Artificial intelligence
Autoencoders
Deep learning
Deepfakes
Face manipulation
Forensics
GAN
Survey
Deep learning
Deepfakes
Survey
Face manipulation
Forensics
Autoencoders
GAN
Artificial intelligence
ISSN:1077-3142, 1090-235X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning has been successfully applied to solve various complex problems ranging from big data analytics to computer vision and human-level control. Deep learning advances however have also been employed to create software that can cause threats to privacy, democracy and national security. One of those deep learning-powered applications recently emerged is deepfake. Deepfake algorithms can create fake images and videos that humans cannot distinguish them from authentic ones. The proposal of technologies that can automatically detect and assess the integrity of digital visual media is therefore indispensable. This paper presents a survey of algorithms used to create deepfakes and, more importantly, methods proposed to detect deepfakes in the literature to date. We present extensive discussions on challenges, research trends and directions related to deepfake technologies. By reviewing the background of deepfakes and state-of-the-art deepfake detection methods, this study provides a comprehensive overview of deepfake techniques and facilitates the development of new and more robust methods to deal with the increasingly challenging deepfakes. •Technologies for creating deepfakes are increasingly approachable.•Automatic assessment of the integrity of digital visual media is indispensable.•Present a survey of algorithms used to create and detect deepfakes.•Extensively discuss the challenges and research directions related to deepfakes.•Facilitate the development of effective methods to deal with challenging deepfakes.
ISSN:1077-3142
1090-235X
DOI:10.1016/j.cviu.2022.103525