Year: 2025
Type: conference-paper
Abstract: Modern text-to-image (T2I) diffusion models can generate images with remarkable realism and creativity. These advancements have sparked research in fake image detection and attribution, yet prior studies have not fully explored the practical and scientific dimensions of this task. In addition to attributing images to 12 state-of-the-art T2I generators, we provide extensive analyses on what inference stage hyperparameters and image modifications are discernible. Our experiments reveal that initialization seeds are highly detectable, along with other subtle variations in the image generation process to some extent. We further investigate what visual traces are leveraged in image attribution by perturbing high-frequency details and employing midlevel representations of image style and structure. Notably, altering high-frequency information causes only slight reductions in accuracy, and training an attributor on style representations outperforms training on RGB images. Our analyses underscore that fake images are detectable and attributable at various levels of visual granularity.
Authors: Katherine Xu, Lingzhi Zhang, Jianbo Shi
Institutions: University of Pennsylvania, Adobe Systems (United States)
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4409262697