Year: 2025
Type: article
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.
Source: Theoretical and Natural Science
Authors: Nan Wang, Xiawei Liu, Yingtan Ji, Ye Zheng
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410128788