articleProceedings of the National Academy of SciencesFeb 14, 2022HYBRID OA

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

Lancaster University · University of California, Berkeley

PubMed
Indexed incrossrefpubmed

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.

Citation impact

338
total citations
FWCI
29.63
Percentile
100%
References
14
Citations per year

Authors

2

Topics & keywords

Keywords
  • Trustworthiness
  • Disinformation
  • Uncanny valley
  • Computer science
  • Uncanny
  • Artificial intelligence
  • Computer security
  • Computer vision
UN Sustainable Development Goals
  • Peace, Justice and strong institutions
No related works found for this paper.