Download pdf
Alias-Free Generative Adversarial Networks’ Generated Picture Detection
- 1 College of Letters and Science, University of California, Davis, 95618, United States
- 2 Viterbi School of Engineering, University of Southern California, Los Angeles, 90089, United States
- 3 Faculty of Science and Technology, Beijing Normal University-Hong Kong Baptist University United International College (UIC), Zhuhai, 519087, China
- 4 College of Information Science and Technology, Taishan University, Taian, 271000, China
* Author to whom correspondence should be addressed.
Abstract
This paper explores the ability of humans to distinguish between images generated by Alias-Free Generative Adversarial Networks (StyleGAN3) and real photographs. It focuses on human accuracy in correctly identifying "fake" images, aiming to assess the authenticity and detectability of pictures produced by the StyleGAN3 model. The study involves a comprehensive analysis of various factors influencing human detection capabilities, including image quality, complexity, and contextual cues. By conducting double blind experiments with our group members, the research seeks to identify patterns in misclassification and understand the limitations of human perception in the face of advanced AI-generated content. The findings have significant implications for the fields of digital media, cybersecurity, and the ethical deployment of AI technologies, highlighting the need for improved detection tools and guidelines for AI-generated imagery.
Keywords
Alias-Free Generative Adversarial Networks (GANs), StyleGAN3 Image Generation, Human Detection Accuracy, AI-Generated Image Realism
[1]. Karras, Tero, et al. "Alias-free generative adversarial networks." Advances in neural information processing systems 34 (2021): 852-863.
[2]. Connor R ,Dearle A ,Claydon B , et al.Correlations of Cross-Entropy Loss in Machine Learning[J].Entropy,2024,26(6):491-.
[3]. Karras, Tero, et al. “Analyzing and Improving the Image Quality of StyleGAN” Computer Vision and Pattern Recognition arXiv:1912.04958 [cs.CV]
[4]. Wang, Y., Jiang, L., & Loy, C. C. (2023). Styleinv: A temporal style modulated inversion network for unconditional video generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 22851-22861).
[5]. Bermano, Amit H., et al. "State‐of‐the‐Art in the Architecture, Methods and Applications of StyleGAN." Computer Graphics Forum. Vol. 41. No. 2. 2022.
Cite this article
Wang,N.;Liu,X.;Ji,Y.;Zheng,Y. (2025). Alias-Free Generative Adversarial Networks’ Generated Picture Detection. Theoretical and Natural Science,107,164-170.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 4th International Conference on Computing Innovation and Applied Physics
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).