Human Performance in Deepfake Detection: A Systematic Review

Deepfakes refer to a wide range of computer-generated synthetic media, in which a person’s appearance or likeness is altered to resemble that of another. This systematic review is aimed at providing an overview of the existing research into people’s ability to detect deepfakes. Five databases (IEEE,...

Full description

Saved in:
Bibliographic Details
Main Authors: Klaire Somoray, Dan J. Miller, Mary Holmes
Format: Article
Language:English
Published: Wiley 2025-01-01
Series:Human Behavior and Emerging Technologies
Online Access:http://dx.doi.org/10.1155/hbe2/1833228
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850032744712634368
author Klaire Somoray
Dan J. Miller
Mary Holmes
author_facet Klaire Somoray
Dan J. Miller
Mary Holmes
author_sort Klaire Somoray
collection DOAJ
description Deepfakes refer to a wide range of computer-generated synthetic media, in which a person’s appearance or likeness is altered to resemble that of another. This systematic review is aimed at providing an overview of the existing research into people’s ability to detect deepfakes. Five databases (IEEE, ProQuest, PubMed, Web of Science, and Scopus) were searched up to December 2023. Studies were included if they (1) were an original study; (2) were reported in English; (3) examined people’s detection of deepfakes; (4) examined the influence of an intervention, strategy, or variable on deepfake detection; and (5) reported relevant data needed to evaluate detection accuracy. Forty independent studies from 30 unique records were included in the review. Results were narratively summarized, with key findings organized based on the review’s research questions. Studies used different performance measures, making it difficult to compare results across the literature. Detection accuracy varies widely, with some studies showing humans outperforming AI models and others indicating the opposite. Detection performance is also influenced by person-level (e.g., cognitive ability, analytical thinking) and stimuli-level factors (e.g., quality of deepfake, familiarity with the subject). Interventions to improve people’s deepfake detection yielded mixed results. Humans and AI-based detection models focus on different aspects when detecting, suggesting a potential for human–AI collaboration. The findings highlight the complex interplay of factors influencing human deepfake detection and the need for further research to develop effective strategies for deepfake detection.
format Article
id doaj-art-4dac2c82aaf54b88bf3d50ba9520a877
institution DOAJ
issn 2578-1863
language English
publishDate 2025-01-01
publisher Wiley
record_format Article
series Human Behavior and Emerging Technologies
spelling doaj-art-4dac2c82aaf54b88bf3d50ba9520a8772025-08-20T02:58:32ZengWileyHuman Behavior and Emerging Technologies2578-18632025-01-01202510.1155/hbe2/1833228Human Performance in Deepfake Detection: A Systematic ReviewKlaire Somoray0Dan J. Miller1Mary Holmes2James Cook University College of Healthcare SciencesJames Cook University College of Healthcare SciencesJames Cook University College of Healthcare SciencesDeepfakes refer to a wide range of computer-generated synthetic media, in which a person’s appearance or likeness is altered to resemble that of another. This systematic review is aimed at providing an overview of the existing research into people’s ability to detect deepfakes. Five databases (IEEE, ProQuest, PubMed, Web of Science, and Scopus) were searched up to December 2023. Studies were included if they (1) were an original study; (2) were reported in English; (3) examined people’s detection of deepfakes; (4) examined the influence of an intervention, strategy, or variable on deepfake detection; and (5) reported relevant data needed to evaluate detection accuracy. Forty independent studies from 30 unique records were included in the review. Results were narratively summarized, with key findings organized based on the review’s research questions. Studies used different performance measures, making it difficult to compare results across the literature. Detection accuracy varies widely, with some studies showing humans outperforming AI models and others indicating the opposite. Detection performance is also influenced by person-level (e.g., cognitive ability, analytical thinking) and stimuli-level factors (e.g., quality of deepfake, familiarity with the subject). Interventions to improve people’s deepfake detection yielded mixed results. Humans and AI-based detection models focus on different aspects when detecting, suggesting a potential for human–AI collaboration. The findings highlight the complex interplay of factors influencing human deepfake detection and the need for further research to develop effective strategies for deepfake detection.http://dx.doi.org/10.1155/hbe2/1833228
spellingShingle Klaire Somoray
Dan J. Miller
Mary Holmes
Human Performance in Deepfake Detection: A Systematic Review
Human Behavior and Emerging Technologies
title Human Performance in Deepfake Detection: A Systematic Review
title_full Human Performance in Deepfake Detection: A Systematic Review
title_fullStr Human Performance in Deepfake Detection: A Systematic Review
title_full_unstemmed Human Performance in Deepfake Detection: A Systematic Review
title_short Human Performance in Deepfake Detection: A Systematic Review
title_sort human performance in deepfake detection a systematic review
url http://dx.doi.org/10.1155/hbe2/1833228
work_keys_str_mv AT klairesomoray humanperformanceindeepfakedetectionasystematicreview
AT danjmiller humanperformanceindeepfakedetectionasystematicreview
AT maryholmes humanperformanceindeepfakedetectionasystematicreview