Training-free Source Attribution of AI-generated Images via Resynthesis

Synthetic image source attribution is a challenging task, especially in data scarcity conditions requiring few-shot or zero-shot classification capabilities. We present a new training-free one-shot attribution method based on image resynthesis. A prompt describing the image under analysis is generated, then it is used to resynthesize the image with all the candidate sources. The image is attributed to the model which produced the resynthesis closest to the original image in a proper feature space. We also introduce a new dataset for synthetic image attribution consisting of face images from commercial and open-source text-to-image generators. The dataset provides a challenging attribution framework, useful for developing new attribution models and testing their capabilities on different generative architectures. The dataset structure allows to test approaches based on resynthesis and to compare them to few-shot methods. Results from state-of-the-art few-shot approaches and other baselines show that the proposed resynthesis method outperforms existing techniques when only a few samples are available for training or fine-tuning. The experiments also demonstrate that the new dataset is a challenging one and represents a valuable benchmark for developing and evaluating future few-shot and zero-shot methods.

Key Contributions

• Training-free, one-shot synthetic image source attribution method that generates image resyntheses with each candidate model and attributes based on minimum CLIP-feature-space distance
• New SIA dataset of face images from 14 sources (7 commercial, 7 open-source text-to-image generators) with paired resyntheses enabling few-shot and zero-shot evaluation
• Comprehensive baselines showing resynthesis method outperforms state-of-the-art few-shot approaches under data scarcity conditions

🛡️ Threat Analysis

Details

Similar Papers