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

Author:

Miller Elizabeth J.1ORCID,Steward Ben A.1ORCID,Witkower Zak2ORCID,Sutherland Clare A. M.34ORCID,Krumhuber Eva G.5ORCID,Dawel Amy1ORCID

Affiliation:

1. School of Medicine and Psychology, Australian National University

2. Department of Psychology, University of Toronto

3. School of Psychology, King’s College, University of Aberdeen

4. School of Psychological Science, University of Western Australia

5. Department of Experimental Psychology, University College London

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.

Funder

Australian Research Council

Australian National University

Experimental Psychology Society

Publisher

SAGE Publications

Subject

General Psychology

Reference44 articles.

1. Reverse engineering the face space: Discovering the critical features for face identification

2. Bond S. (2023, March 23). It takes a few dollars and 8 minutes to create a deepfake. And that’s only the start. NPR. https://www.npr.org/2023/03/23/1165146797/it-takes-a-few-dollars-and-8-minutes-to-create-a-deepfake-and-thats-only-the-sta

3. Using thematic analysis in psychology

4. Perception and the Representative Design of Psychological Experiments

5. Identity From Variation: Representations of Faces Derived From Multiple Instances

Cited by 19 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3