Understanding Users’ Deepfake Video Verification Strategies

Dion Hoe Lian Goh; Chei Sian Lee; Zirong Chen; Xue Wen Kuah; Ying Ling Pang

doi:10.1007/978-3-031-19682-9_4

Understanding Users’ Deepfake Video Verification Strategies

Dion Hoe Lian Goh, Chei Sian Lee^*, Zirong Chen, Xue Wen Kuah, Ying Ling Pang

^*Corresponding author for this work

Nanyang Technological University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

Abstract

Deepfakes are synthetically generated media that pose as actual video recordings, and are a potential source of fake news or disinformation. Consequently, the ability to detect them is imperative. Although research has been done in creating algorithms for automatic detection, there is little work conducted on how users identify deepfakes. Hence, the present paper fills this gap with a user study. Through semi-structured interviews, participants were asked to identify real and deepfake videos, and explain how they arrived at their conclusions. Seven verification strategies emerged, with the most popular being the use of subtle indictors in the videos suggesting the presence of imperfections. The use of one’s social circle to verify a video was the least used. Surprisingly, only half our participants could correctly identify all the videos they watched. Deepfake videos that seemed to portray believable content or were of high quality made participants think they were real.

Original language	English
Title of host publication	HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings
Editors	Constantine Stephanidis, Margherita Antona, Stavroula Ntoa, Gavriel Salvendy
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	25-32
Number of pages	8
ISBN (Print)	9783031196812
DOIs	https://doi.org/10.1007/978-3-031-19682-9_4
Publication status	Published - 2022
Externally published	Yes
Event	24th International Conference on Human-Computer Interaction, HCII 2022 - Virtual, Online Duration: Jun 26 2022 → Jul 1 2022

Publication series

Name	Communications in Computer and Information Science
Volume	1655 CCIS
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	24th International Conference on Human-Computer Interaction, HCII 2022
City	Virtual, Online
Period	6/26/22 → 7/1/22

Bibliographical note

Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

ASJC Scopus Subject Areas

General Computer Science
General Mathematics

Keywords

Authenticity
Deepfake videos
Identification
User study
Verification strategies

Access to Document

10.1007/978-3-031-19682-9_4

Cite this

Goh, D. H. L., Lee, C. S., Chen, Z., Kuah, X. W., & Pang, Y. L. (2022). Understanding Users’ Deepfake Video Verification Strategies. In C. Stephanidis, M. Antona, S. Ntoa, & G. Salvendy (Eds.), HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings (pp. 25-32). (Communications in Computer and Information Science; Vol. 1655 CCIS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-19682-9_4

Goh, Dion Hoe Lian ; Lee, Chei Sian ; Chen, Zirong et al. / Understanding Users’ Deepfake Video Verification Strategies. HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings. editor / Constantine Stephanidis ; Margherita Antona ; Stavroula Ntoa ; Gavriel Salvendy. Springer Science and Business Media Deutschland GmbH, 2022. pp. 25-32 (Communications in Computer and Information Science).

@inproceedings{98c1ebfc5b274dddbd4bccb77545551f,

title = "Understanding Users{\textquoteright} Deepfake Video Verification Strategies",

abstract = "Deepfakes are synthetically generated media that pose as actual video recordings, and are a potential source of fake news or disinformation. Consequently, the ability to detect them is imperative. Although research has been done in creating algorithms for automatic detection, there is little work conducted on how users identify deepfakes. Hence, the present paper fills this gap with a user study. Through semi-structured interviews, participants were asked to identify real and deepfake videos, and explain how they arrived at their conclusions. Seven verification strategies emerged, with the most popular being the use of subtle indictors in the videos suggesting the presence of imperfections. The use of one{\textquoteright}s social circle to verify a video was the least used. Surprisingly, only half our participants could correctly identify all the videos they watched. Deepfake videos that seemed to portray believable content or were of high quality made participants think they were real.",

keywords = "Authenticity, Deepfake videos, Identification, User study, Verification strategies",

author = "Goh, {Dion Hoe Lian} and Lee, {Chei Sian} and Zirong Chen and Kuah, {Xue Wen} and Pang, {Ying Ling}",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 24th International Conference on Human-Computer Interaction, HCII 2022 ; Conference date: 26-06-2022 Through 01-07-2022",

year = "2022",

doi = "10.1007/978-3-031-19682-9_4",

language = "English",

isbn = "9783031196812",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "25--32",

editor = "Constantine Stephanidis and Margherita Antona and Stavroula Ntoa and Gavriel Salvendy",

booktitle = "HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings",

address = "Germany",

}

Goh, DHL, Lee, CS, Chen, Z, Kuah, XW & Pang, YL 2022, Understanding Users’ Deepfake Video Verification Strategies. in C Stephanidis, M Antona, S Ntoa & G Salvendy (eds), HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings. Communications in Computer and Information Science, vol. 1655 CCIS, Springer Science and Business Media Deutschland GmbH, pp. 25-32, 24th International Conference on Human-Computer Interaction, HCII 2022, Virtual, Online, 6/26/22. https://doi.org/10.1007/978-3-031-19682-9_4

Understanding Users’ Deepfake Video Verification Strategies. / Goh, Dion Hoe Lian; Lee, Chei Sian; Chen, Zirong et al.
HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings. ed. / Constantine Stephanidis; Margherita Antona; Stavroula Ntoa; Gavriel Salvendy. Springer Science and Business Media Deutschland GmbH, 2022. p. 25-32 (Communications in Computer and Information Science; Vol. 1655 CCIS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Understanding Users’ Deepfake Video Verification Strategies

AU - Goh, Dion Hoe Lian

AU - Lee, Chei Sian

AU - Chen, Zirong

AU - Kuah, Xue Wen

AU - Pang, Ying Ling

PY - 2022

Y1 - 2022

N2 - Deepfakes are synthetically generated media that pose as actual video recordings, and are a potential source of fake news or disinformation. Consequently, the ability to detect them is imperative. Although research has been done in creating algorithms for automatic detection, there is little work conducted on how users identify deepfakes. Hence, the present paper fills this gap with a user study. Through semi-structured interviews, participants were asked to identify real and deepfake videos, and explain how they arrived at their conclusions. Seven verification strategies emerged, with the most popular being the use of subtle indictors in the videos suggesting the presence of imperfections. The use of one’s social circle to verify a video was the least used. Surprisingly, only half our participants could correctly identify all the videos they watched. Deepfake videos that seemed to portray believable content or were of high quality made participants think they were real.

AB - Deepfakes are synthetically generated media that pose as actual video recordings, and are a potential source of fake news or disinformation. Consequently, the ability to detect them is imperative. Although research has been done in creating algorithms for automatic detection, there is little work conducted on how users identify deepfakes. Hence, the present paper fills this gap with a user study. Through semi-structured interviews, participants were asked to identify real and deepfake videos, and explain how they arrived at their conclusions. Seven verification strategies emerged, with the most popular being the use of subtle indictors in the videos suggesting the presence of imperfections. The use of one’s social circle to verify a video was the least used. Surprisingly, only half our participants could correctly identify all the videos they watched. Deepfake videos that seemed to portray believable content or were of high quality made participants think they were real.

KW - Authenticity

KW - Deepfake videos

KW - Identification

KW - User study

KW - Verification strategies

UR - http://www.scopus.com/inward/record.url?scp=85144605792&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85144605792&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-19682-9_4

DO - 10.1007/978-3-031-19682-9_4

M3 - Conference contribution

AN - SCOPUS:85144605792

SN - 9783031196812

T3 - Communications in Computer and Information Science

SP - 25

EP - 32

BT - HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings

A2 - Stephanidis, Constantine

A2 - Antona, Margherita

A2 - Ntoa, Stavroula

A2 - Salvendy, Gavriel

PB - Springer Science and Business Media Deutschland GmbH

T2 - 24th International Conference on Human-Computer Interaction, HCII 2022

Y2 - 26 June 2022 through 1 July 2022

ER -

Goh DHL, Lee CS, Chen Z, Kuah XW, Pang YL. Understanding Users’ Deepfake Video Verification Strategies. In Stephanidis C, Antona M, Ntoa S, Salvendy G, editors, HCI International 2022 – Late Breaking Posters - 24th International Conference on Human-Computer Interaction, HCII 2022, Proceedings. Springer Science and Business Media Deutschland GmbH. 2022. p. 25-32. (Communications in Computer and Information Science). doi: 10.1007/978-3-031-19682-9_4

Understanding Users’ Deepfake Video Verification Strategies

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this