Litcius/Paper detail

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

Sophie J. Nightingale, Hany Farid

2022Proceedings of the National Academy of Sciences352 citationsDOIOpen Access PDF

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.

Topics & Concepts

TrustworthinessDisinformationUncanny valleyComputer scienceUncannyArtificial intelligenceComputer securityComputer visionPsychologyWorld Wide WebSocial mediaRobotPsychoanalysisFace recognition and analysisGenerative Adversarial Networks and Image SynthesisLaw in Society and Culture
AI-synthesized faces are indistinguishable from real faces and more trustworthy | Litcius