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

Sophie J Nightingale; Hany Farid

doi:10.1073/pnas.2120481119

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

Proc Natl Acad Sci U S A. 2022 Feb 22;119(8):e2120481119. doi: 10.1073/pnas.2120481119.

Authors

Sophie J Nightingale¹, Hany Farid²

Affiliations

¹ Department of Psychology, Lancaster University, Lancaster LA1 4YW, United Kingdom; s.nightingale1@lancaster.ac.uk.
² Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720.

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.

Keywords: deep fakes; face perception.