AI-synthesized faces are indistinguishable from real faces and more trustworthy
By Sophie J. Nightingale, Hany Farid. Proceedings of the National Academy of Sciences of the United States of America, 2022
364 citations recorded by the source corpus.
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.
Subfields: Computer Vision and Pattern Recognition, Law
View Paper: https://www.semanticscholar.org/paper/59dbb2de2d80ef62d401c2f1cdf05766898b093e
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- A. Engel
- Tony Chiang
- Anand D. Sarwate
- Reilly Cannon
- Max Vargas
- Hany Farid
- Jonas Oppenlaender
- Luisa Verdoliva
In Law
- Hany Farid
- Jonas Oppenlaender
- Luisa Verdoliva
- James F. O'Brien
- Gajanan K. Birajdar
- Vijay Harishchandra Mankar
Citations in the corpus
- The Creativity of Text-to-Image Generation (2022, background): “But it can be expected that we will, in the near future, no longer be able to tell text-toimage artworks apart from creations made by humans [37].”
- Creating, Using, Misusing, and Detecting Deep Fakes (2022, background): “For example, in mid-May of 2020, in the midst of the global pandemic, 20% of the US public believed Bill Gates was planning to use COVID-19 to implement a mandatory vaccine program with tracking microchips (Nightingale and Farid 2020).”
- Understanding generative AI output with embedding models (2025, unknown): “The release of ChatGPT quickly led to noticeable shifts in writing styles ( 60 ), and other studies have issued concerns for the ability of humans to detect articles produced by generative AI models ( 61 – 63 ).”
- Understanding Generative AI Content with Embedding Models (2024, result): “The release of ChatGPT quickly led to noticeable shifts in writing styles [55], with other studies issuing concern on the human ability to detect articles produced by generative models [56–58].”