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

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 throu...

Descripción completa

Detalles Bibliográficos
Autores principales: Nightingale, Sophie J., Farid, Hany
Formato: Online Artículo Texto
Lenguaje:English
Publicado: National Academy of Sciences 2022
Materias:
Social Sciences
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8872790/
https://www.ncbi.nlm.nih.gov/pubmed/35165187
http://dx.doi.org/10.1073/pnas.2120481119
_version_ 1784657324949897216
author Nightingale, Sophie J.
Farid, Hany
author_facet Nightingale, Sophie J.
Farid, Hany
author_sort Nightingale, Sophie J.
collection PubMed
description 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.
format Online
Article
Text
id pubmed-8872790
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher National Academy of Sciences
record_format MEDLINE/PubMed
spelling pubmed-88727902022-02-25 AI-synthesized faces are indistinguishable from real faces and more trustworthy Nightingale, Sophie J. Farid, Hany Proc Natl Acad Sci U S A Social Sciences 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. National Academy of Sciences 2022-02-14 2022-02-22 /pmc/articles/PMC8872790/ /pubmed/35165187 http://dx.doi.org/10.1073/pnas.2120481119 Text en Copyright © 2022 the Author(s). Published by PNAS. https://creativecommons.org/licenses/by-nc-nd/4.0/This open access article is distributed under Creative Commons Attribution-NonCommercial-NoDerivatives License 4.0 (CC BY-NC-ND) (https://creativecommons.org/licenses/by-nc-nd/4.0/) .
spellingShingle Social Sciences
Nightingale, Sophie J.
Farid, Hany
AI-synthesized faces are indistinguishable from real faces and more trustworthy
title AI-synthesized faces are indistinguishable from real faces and more trustworthy
title_full AI-synthesized faces are indistinguishable from real faces and more trustworthy
title_fullStr AI-synthesized faces are indistinguishable from real faces and more trustworthy
title_full_unstemmed AI-synthesized faces are indistinguishable from real faces and more trustworthy
title_short AI-synthesized faces are indistinguishable from real faces and more trustworthy
title_sort ai-synthesized faces are indistinguishable from real faces and more trustworthy
topic Social Sciences
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8872790/
https://www.ncbi.nlm.nih.gov/pubmed/35165187
http://dx.doi.org/10.1073/pnas.2120481119
work_keys_str_mv AT nightingalesophiej aisynthesizedfacesareindistinguishablefromrealfacesandmoretrustworthy
AT faridhany aisynthesizedfacesareindistinguishablefromrealfacesandmoretrustworthy

Ejemplares similares