Challenges and Applications of Face Deepfake

Lamyanba Laishram, Md Maklachur Rahman, Soon Ki Jung

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

With the development of Generative deep learning algorithms in the last decade, it has become increasingly difficult to differentiate between what is real and what is fake. With the easily available “Deepfake” applications, even a person with less computing knowledge can also produce realistic Deepfake data. These fake data have many benefits while on the other hand, it can also be used for unethical and malicious purposes. Deepfake can be anything fake data generated by using deep learning methods. In this study, we focus on Deepfake with respect to face manipulation. We represent the currently used algorithms and datasets are represented for creating Deepfake. We also study the challenges and the real-world applications in which the benefits, as well as the drawbacks of using Deepfake, are being pointed out.

Original languageEnglish
Title of host publicationFrontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers
EditorsHieyong Jeong, Kazuhiko Sumi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages131-156
Number of pages26
ISBN (Print)9783030816377
DOIs
StatePublished - 2021
Event27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021 - Virtual, Online
Duration: 22 Feb 202123 Feb 2021

Publication series

NameCommunications in Computer and Information Science
Volume1405
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021
CityVirtual, Online
Period22/02/2123/02/21

Keywords

  • Deepfake
  • DeepFake creation
  • Deepfake dataset
  • Face attribute editing
  • Faceswap

Fingerprint

Dive into the research topics of 'Challenges and Applications of Face Deepfake'. Together they form a unique fingerprint.

Cite this