Home > Research > Publications & Outputs > AI-synthesized faces are indistinguishable from...

Research

Associated organisational unit

Electronic data

  • NightingaleFarid2022

    Final published version, 1.18 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

AI-synthesized faces are indistinguishable from real faces and more trustworthy

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

AI-synthesized faces are indistinguishable from real faces and more trustworthy. / Nightingale, Sophie; Farid, Hany.
In: Proceedings of the National Academy of Sciences of the United States of America, Vol. 119, No. 8, e2120481119, 22.02.2022.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Nightingale, S & Farid, H 2022, 'AI-synthesized faces are indistinguishable from real faces and more trustworthy', Proceedings of the National Academy of Sciences of the United States of America, vol. 119, no. 8, e2120481119. https://doi.org/10.1073/pnas.2120481119

APA

Nightingale, S., & Farid, H. (2022). AI-synthesized faces are indistinguishable from real faces and more trustworthy. Proceedings of the National Academy of Sciences of the United States of America, 119(8), Article e2120481119. https://doi.org/10.1073/pnas.2120481119

Vancouver

Nightingale S, Farid H. AI-synthesized faces are indistinguishable from real faces and more trustworthy. Proceedings of the National Academy of Sciences of the United States of America. 2022 Feb 22;119(8):e2120481119. Epub 2022 Feb 14. doi: 10.1073/pnas.2120481119

Author

Nightingale, Sophie ; Farid, Hany. / AI-synthesized faces are indistinguishable from real faces and more trustworthy. In: Proceedings of the National Academy of Sciences of the United States of America. 2022 ; Vol. 119, No. 8.

Bibtex

@article{6d3fda22557a4f23a4945e154666fcf9,
title = "AI-synthesized faces are indistinguishable from real faces and more trustworthy",
abstract = "Artificial intelligence (AI)–synthesized text, audio, image, and video are being weaponized for the purposes of nonconsensual intimate imagery, financial fraud, and disinformation campaigns. Our evaluation of the photorealism of AI-synthesized faces indicates that synthesis engines have passed through the uncanny valley and are capable of creating faces that are indistinguishable—and more trustworthy—than real faces.",
author = "Sophie Nightingale and Hany Farid",
year = "2022",
month = feb,
day = "22",
doi = "10.1073/pnas.2120481119",
language = "English",
volume = "119",
journal = "Proceedings of the National Academy of Sciences of the United States of America",
issn = "0027-8424",
publisher = "National Academy of Sciences",
number = "8",

}

RIS

TY - JOUR

T1 - AI-synthesized faces are indistinguishable from real faces and more trustworthy

AU - Nightingale, Sophie

AU - Farid, Hany

PY - 2022/2/22

Y1 - 2022/2/22

N2 - Artificial intelligence (AI)–synthesized text, audio, image, and video are being weaponized for the purposes of nonconsensual intimate imagery, financial fraud, and disinformation campaigns. Our evaluation of the photorealism of AI-synthesized faces indicates that synthesis engines have passed through the uncanny valley and are capable of creating faces that are indistinguishable—and more trustworthy—than real faces.

AB - Artificial intelligence (AI)–synthesized text, audio, image, and video are being weaponized for the purposes of nonconsensual intimate imagery, financial fraud, and disinformation campaigns. Our evaluation of the photorealism of AI-synthesized faces indicates that synthesis engines have passed through the uncanny valley and are capable of creating faces that are indistinguishable—and more trustworthy—than real faces.

U2 - 10.1073/pnas.2120481119

DO - 10.1073/pnas.2120481119

M3 - Journal article

VL - 119

JO - Proceedings of the National Academy of Sciences of the United States of America

JF - Proceedings of the National Academy of Sciences of the United States of America

SN - 0027-8424

IS - 8

M1 - e2120481119

ER -