Skip to main content

Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review

Altuncu, Enes and Franqueira, Virginia N. L. and Li, Shujun (2022) Deepfake: Definitions, Performance Metrics and Standards, Datasets and Benchmarks, and a Meta-Review. [Preprint] (doi:10.48550/arXiv.2208.10913) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided) (KAR id:97945)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided.
Official URL:
https://doi.org/10.48550/arXiv.2208.10913

Abstract

Recent advancements in AI, especially deep learning, have contributed to a significant increase in the creation of new realistic-looking synthetic media (video, image, and audio) and manipulation of existing media, which has led to the creation of the new term ``deepfake''. Based on both the research literature and resources in English and in Chinese, this paper gives a comprehensive overview of deepfake, covering multiple important aspects of this emerging concept, including 1) different definitions, 2) commonly used performance metrics and standards, and 3) deepfake-related datasets, challenges, competitions and benchmarks. In addition, the paper also reports a meta-review of 12 selected deepfake-related survey papers published in 2020 and 2021, focusing not only on the mentioned aspects, but also on the analysis of key challenges and recommendations. We believe that this paper is the most comprehensive review of deepfake in terms of aspects covered, and the first one covering both the English and Chinese literature and sources.

Item Type: Preprint
DOI/Identification number: 10.48550/arXiv.2208.10913
Refereed: No
Other identifier: https://arxiv.org/abs/2208.10913
Name of pre-print platform: arXiv
Uncontrolled keywords: Deepfake, Survey, Definition, Datasets, Benchmarks, Challenges, Competitions, Standards, Performance Metrics
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.575 Multimedia systems
Q Science > QA Mathematics (inc Computing science) > QA 76 Software, computer programming, > QA76.87 Neural computers, neural networks
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
University-wide institutes > Institute of Cyber Security for Society
Funders: University of Kent (https://ror.org/00xkeyj56)
Depositing User: Virginia Franqueira
Date Deposited: 13 Nov 2022 14:23 UTC
Last Modified: 10 Oct 2023 11:09 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/97945 (The current URI for this page, for reference purposes)

University of Kent Author Information

Altuncu, Enes.

Creator's ORCID:
CReDIT Contributor Roles:

Franqueira, Virginia N. L..

Creator's ORCID: https://orcid.org/0000-0003-1332-9115
CReDIT Contributor Roles:

Li, Shujun.

Creator's ORCID: https://orcid.org/0000-0001-5628-7328
CReDIT Contributor Roles:
  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.