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

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/MagazineJournal articlepeer-review

Published
Article numbere2120481119
<mark>Journal publication date</mark>22/02/2022
<mark>Journal</mark>Proceedings of the National Academy of Sciences of the United States of America
Issue number8
Volume119
Number of pages3
Publication StatusPublished
Early online date14/02/22
<mark>Original language</mark>English

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.