AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones

Elizabeth J. Miller; Ben A. Steward; Zak Witkower; Clare A. M. Sutherland; Eva G. Krumhuber; Amy Dawel

doi:10.1177/09567976231207095

AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones

Elizabeth J. Miller, Ben A. Steward, Zak Witkower, Clare A. M. Sutherland, Eva G. Krumhuber, Amy Dawel^* (Corresponding Author)

^*Corresponding author for this work

Psychology

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

4 Downloads (Pure)

Abstract

Recent evidence shows that AI-generated faces are now indistinguishable from human faces. However, algorithms are trained disproportionately on White faces, and thus White AI faces may appear especially realistic. In Experiment 1 (N = 124 adults), alongside our reanalysis of previously published data, we showed that White AI faces are judged as human more often than actual human faces—a phenomenon we term AI hyperrealism. Paradoxically, people who made the most errors in this task were the most confident (a Dunning-Kruger effect). In Experiment 2 (N = 610 adults), we used face-space theory and participant qualitative reports to identify key facial attributes that distinguish AI from human faces but were misinterpreted by participants, leading to AI hyperrealism. However, the attributes permitted high accuracy using machine learning. These findings illustrate how psychological theory can inform understanding of AI outputs and provide direction for debiasing AI algorithms, thereby promoting the ethical use of AI.

Original language	English
Pages (from-to)	1390-1403
Number of pages	14
Journal	Psychological Science
Volume	34
Issue number	12
Early online date	13 Nov 2023
DOIs	https://doi.org/10.1177/09567976231207095
Publication status	Published - 1 Dec 2023

Bibliographical note

Acknowledgment
We thank Sophie J. Nightingale and Hany Farid for providing open access to their stimuli and data.

Funding
This research is supported by the Australian Government through the Australian Research Council’s Discovery Projects funding scheme (Project No. DP220101026), a TRANSFORM Career Development Fellowship to A. Dawel from the Australian National University College of Health and Medicine, and an Experimental Psychology Society Small Grant to C. A. M. Sutherland. The funders had no role in developing or conducting this research.

Data Availability Statement

Supplemental materials
Additional supporting information can be found at https://journals.sagepub.com/doi/full/10.1177/09567976231207095

Open Practices
This article has received the badges for Open Data and Open Materials. More information about the Open Practices badges can be found at http://www.psychologicalscience.org/publications/badges.

Keywords

StyleGAN2
artificial intelligence
face perception
face-space theory
generative adversarial network
open data
open materials

Access to Document

10.1177/09567976231207095Licence: CC BY-NC

Miller_etal_PS_AI_Hyperrealism_Why_VoR
This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).
Final published version, 1.49 MBLicence: CC BY-NC

Data From AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones
Miller, J. E. (Creator), Steward, B. A. (Creator), Witkower, Z. (Creator), Sutherland, C. (Creator), Krumhuber, E. G. (Creator) & Dawel, A. (Creator), University of Aberdeen, 3 Nov 2023
DOI: 10.1177/095679762312070, https://journals.sagepub.com/doi/suppl/10.1177/09567976231207095/suppl_file/sj-pdf-1-pss-10.1177_09567976231207095.pdf
Dataset

Cite this

@article{f620f3c6ad43446ebf6974817b89db89,

title = "AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones",

abstract = "Recent evidence shows that AI-generated faces are now indistinguishable from human faces. However, algorithms are trained disproportionately on White faces, and thus White AI faces may appear especially realistic. In Experiment 1 (N = 124 adults), alongside our reanalysis of previously published data, we showed that White AI faces are judged as human more often than actual human faces—a phenomenon we term AI hyperrealism. Paradoxically, people who made the most errors in this task were the most confident (a Dunning-Kruger effect). In Experiment 2 (N = 610 adults), we used face-space theory and participant qualitative reports to identify key facial attributes that distinguish AI from human faces but were misinterpreted by participants, leading to AI hyperrealism. However, the attributes permitted high accuracy using machine learning. These findings illustrate how psychological theory can inform understanding of AI outputs and provide direction for debiasing AI algorithms, thereby promoting the ethical use of AI.",

keywords = "StyleGAN2, artificial intelligence, face perception, face-space theory, generative adversarial network, open data, open materials",

author = "Miller, {Elizabeth J.} and Steward, {Ben A.} and Zak Witkower and Sutherland, {Clare A. M.} and Krumhuber, {Eva G.} and Amy Dawel",

note = "Acknowledgment We thank Sophie J. Nightingale and Hany Farid for providing open access to their stimuli and data. Funding This research is supported by the Australian Government through the Australian Research Council{\textquoteright}s Discovery Projects funding scheme (Project No. DP220101026), a TRANSFORM Career Development Fellowship to A. Dawel from the Australian National University College of Health and Medicine, and an Experimental Psychology Society Small Grant to C. A. M. Sutherland. The funders had no role in developing or conducting this research.",

year = "2023",

month = dec,

day = "1",

doi = "10.1177/09567976231207095",

language = "English",

volume = "34",

pages = "1390--1403",

journal = "Psychological Science",

issn = "0956-7976",

publisher = "SAGE Publications Inc.",

number = "12",

}

TY - JOUR

T1 - AI Hyperrealism

T2 - Why AI Faces Are Perceived as More Real Than Human Ones

AU - Miller, Elizabeth J.

AU - Steward, Ben A.

AU - Witkower, Zak

AU - Sutherland, Clare A. M.

AU - Krumhuber, Eva G.

AU - Dawel, Amy

N1 - Acknowledgment We thank Sophie J. Nightingale and Hany Farid for providing open access to their stimuli and data. Funding This research is supported by the Australian Government through the Australian Research Council’s Discovery Projects funding scheme (Project No. DP220101026), a TRANSFORM Career Development Fellowship to A. Dawel from the Australian National University College of Health and Medicine, and an Experimental Psychology Society Small Grant to C. A. M. Sutherland. The funders had no role in developing or conducting this research.

PY - 2023/12/1

Y1 - 2023/12/1

N2 - Recent evidence shows that AI-generated faces are now indistinguishable from human faces. However, algorithms are trained disproportionately on White faces, and thus White AI faces may appear especially realistic. In Experiment 1 (N = 124 adults), alongside our reanalysis of previously published data, we showed that White AI faces are judged as human more often than actual human faces—a phenomenon we term AI hyperrealism. Paradoxically, people who made the most errors in this task were the most confident (a Dunning-Kruger effect). In Experiment 2 (N = 610 adults), we used face-space theory and participant qualitative reports to identify key facial attributes that distinguish AI from human faces but were misinterpreted by participants, leading to AI hyperrealism. However, the attributes permitted high accuracy using machine learning. These findings illustrate how psychological theory can inform understanding of AI outputs and provide direction for debiasing AI algorithms, thereby promoting the ethical use of AI.

AB - Recent evidence shows that AI-generated faces are now indistinguishable from human faces. However, algorithms are trained disproportionately on White faces, and thus White AI faces may appear especially realistic. In Experiment 1 (N = 124 adults), alongside our reanalysis of previously published data, we showed that White AI faces are judged as human more often than actual human faces—a phenomenon we term AI hyperrealism. Paradoxically, people who made the most errors in this task were the most confident (a Dunning-Kruger effect). In Experiment 2 (N = 610 adults), we used face-space theory and participant qualitative reports to identify key facial attributes that distinguish AI from human faces but were misinterpreted by participants, leading to AI hyperrealism. However, the attributes permitted high accuracy using machine learning. These findings illustrate how psychological theory can inform understanding of AI outputs and provide direction for debiasing AI algorithms, thereby promoting the ethical use of AI.

KW - StyleGAN2

KW - artificial intelligence

KW - face perception

KW - face-space theory

KW - generative adversarial network

KW - open data

KW - open materials

U2 - 10.1177/09567976231207095

DO - 10.1177/09567976231207095

M3 - Article

C2 - 37955384

SN - 0956-7976

VL - 34

SP - 1390

EP - 1403

JO - Psychological Science

JF - Psychological Science

IS - 12

ER -

AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones

Abstract

Bibliographical note

Data Availability Statement

Keywords

Access to Document

Fingerprint

Datasets

Data From AI Hyperrealism: Why AI Faces Are Perceived as More Real Than Human Ones

Cite this