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

Nightingale, Sophie and Farid, Hany (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). ISSN 0027-8424

[img]
Text (NightingaleFarid2022)
NightingaleFarid2022.pdf - Published Version
Available under License Creative Commons Attribution-NonCommercial-NoDerivs.

Download (1MB)

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.

Item Type:
Journal Article
Journal or Publication Title:
Proceedings of the National Academy of Sciences of the United States of America
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1000
Subjects:
ID Code:
166271
Deposited By:
Deposited On:
18 Feb 2022 10:00
Refereed?:
Yes
Published?:
Published
Last Modified:
19 May 2022 01:40