Open AccessAI-synthesized faces are indistinguishable from real faces and more trustworthy
Author(s) -
Sophie J. Nightingale,
Hany Farid
Publication year - 2022
Publication title -
proceedings of the national academy of sciences of the united states of america
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.011
H-Index - 771
eISSN - 1091-6490
pISSN - 0027-8424
DOI - 10.1073/pnas.2120481119
Subject(s) - trustworthiness , disinformation , uncanny valley , computer science , uncanny , artificial intelligence , computer security , computer vision , psychology , world wide web , social media , robot , psychoanalysis
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.