Can You Spot the AI-Generated Images? Distinguishing Fake Images Using Signal Detection Theory

被引：0

作者：

Park, Hayun ^{[1
]}

Kim, Gayoung ^{[1
]}

Fee, Danbi ^{[1
]}

Kiw, Hyun K. ^{[1
,2
]}

机构：

[1] Kwangwoon Univ, Dept Artificial Intelligence Applicat, Seoul 01897, South Korea

[2] Kwangwoon Univ, Sch Informat Convergence, Seoul 01897, South Korea

来源：

CROSS-CULTURAL DESIGN, PT IV, CCD 2024 | 2024年 / 14702卷

基金：

新加坡国家研究基金会;

关键词：

Artificial Intelligence; AI-generated image; User experience; Signal Detection Theory; Human AI Interaction;

D O I：

10.1007/978-3-031-60913-8_21

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This study explores individuals' ability to differentiate between AI-generated and genuine human images, with a specific emphasis on different emotional states (lack of emotion, positive emotion, and negative emotion) and human behaviors (postures and activities). An experiment involving 18 participants was conducted to discern various AI-generated human images, and the results were analyzed using signal detection theory. The analysis revealed a significant variation in sensitivity (d') based on the emotional content, with images displaying positive emotions exhibiting notably higher sensitivity compared to emotionless images. No significant sensitivity difference was observed concerning different types of behaviors. Furthermore, there were no significant variations in bias (beta) in relation to emotional states and behaviors. This study holds promise for informing various user experience investigations associated with AI image generators.

引用

页码：299 / 313

页数：15

共 44 条

[21] The Role of AI Attribution Knowledge in the Evaluation of Artwork [J].

Gangadharbatla, Harsha .

EMPIRICAL STUDIES OF THE ARTS, 2022, 40 (02) :125-142

[22]

Ghosh A, 2022, Arxiv, DOI [arXiv:2209.07667, 10.48550/arXiv.2209.07667]

[23]

Gioti Artemi-Maria., 2021, Handbook of Artificial Intelligence for Music, P53

[24]

Hernandez-Olivan C., 2021, arXiv, DOI DOI 10.48550/ARXIV.2108.12290

[25] Artificial Intelligence, Artists, and Art: Attitudes Toward Artwork Produced by Humans vs. Artificial Intelligence [J].

Hong, Joo-Wha ;

Curran, Nathaniel Ming .

ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2019, 15 (02)

[26]

Huang C.-F., 2020, 2020 IEEE EUR C IOT

[27] Generative Artificial Intelligence: Trends and Prospects [J].

Jovanovic, Mladan ;

Campbell, Mark .

COMPUTER, 2022, 55 (10) :107-112

[28] More Real Than Real: A Study on Human Visual Perception of Synthetic Faces [Applications Corner] [J].

Lago, Federica ;

Pasquini, Cecilia ;

Bohme, Rainer ;

Dumont, Helene ;

Goffaux, Valerie ;

Boato, Giulia .

IEEE SIGNAL PROCESSING MAGAZINE, 2022, 39 (01) :109-116

[29]

Li B., 2019, arXiv, DOI DOI 10.48550/ARXIV.1909.07083

[30]

Lu ZY, 2023, Arxiv, DOI arXiv:2304.13023

← 1 2 3 4 5 →