Files and links (1)
Preprint (Author's original)arXiv.org - Non-exclusive license to distribute, Open
Preprint
Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images
26 Mar 2025
Abstract
The emergence of advanced AI-based tools to generate realistic images poses significant challenges for forensic detection and source attribution, especially as new generative techniques appear rapidly. Traditional methods often fail to generalize to unseen generators due to reliance on features specific to known sources during training. To address this problem, we propose a novel approach that explicitly models forensic microstructures - subtle, pixel-level patterns unique to the image creation process. Using only real images in a self-supervised manner, we learn a set of diverse predictive filters to extract residuals that capture different aspects of these microstructures. By jointly modeling these residuals across multiple scales, we obtain a compact model whose parameters constitute a unique forensic self-description for each image. This self-description enables us to perform zero-shot detection of synthetic images, open-set source attribution of images, and clustering based on source without prior knowledge. Extensive experiments demonstrate that our method achieves superior accuracy and adaptability compared to competing techniques, advancing the state of the art in synthetic media forensics.
Metrics
6 Record Views
Details
- Title
- Forensic Self-Descriptions Are All You Need for Zero-Shot Detection, Open-Set Source Attribution, and Clustering of AI-generated Images
- Creators
- Tai D NguyenAref AzizpourMatthew C Stamm
- Resource Type
- Preprint
- Language
- English
- Academic Unit
- Electrical and Computer Engineering; Computer Science
- Other Identifier
- 991022042271404721