Deepfake and Security of Video Conferences

Ahmet Semih Uçan, Fatih Mustafa Buçak, Mehmet Ali Han Tutuk, Haus Ibrahim Aydm, Ertugrul Semiz, Şerif Bahtiyar

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

5 Citations (Scopus)

Abstract

Deep learning is widely used to create artificial contents on the Internet. Similarly, it is also used to detect fake contents. Fake frames created and integrated with deep learning algorithms are known as deepfake. Recently, malicious users tend to use deepfake to manipulate genuine contents to carry out variety of attacks. Video conferencing apphcations has been a significant target of the malicious users since the beginning of Covid-19 pandemic who use deepfake models to create fake virtual identities in onhne video conferences. We propose a lightweight deepfake detection model that may be integrated with video conference applications to detect fake faces. Experimental analyses show that the proposed model provides acceptable accuracy to detect fake images on video conferences.

Original languageEnglish
Title of host publicationProceedings - 6th International Conference on Computer Science and Engineering, UBMK 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages36-41
Number of pages6
ISBN (Electronic)9781665429085
DOIs
Publication statusPublished - 2021
Event6th International Conference on Computer Science and Engineering, UBMK 2021 - Ankara, Turkey
Duration: 15 Sept 202117 Sept 2021

Publication series

NameProceedings - 6th International Conference on Computer Science and Engineering, UBMK 2021

Conference

Conference6th International Conference on Computer Science and Engineering, UBMK 2021
Country/TerritoryTurkey
CityAnkara
Period15/09/2117/09/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE

Keywords

  • Deepfake
  • Detection
  • Inception-Resnet
  • Machine Learning
  • Security
  • Video Conference

Fingerprint

Dive into the research topics of 'Deepfake and Security of Video Conferences'. Together they form a unique fingerprint.

Cite this