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

arXiv: https://arxiv.org/abs/2510.24278 · HTML: https://mlsanity.com/paper/2510.24278/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis](https://mlsanity.com/paper/2310.00426/) (2023)
- [Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding](https://mlsanity.com/paper/2405.08748/) (2024)
- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation](https://mlsanity.com/paper/2402.17245/) (2024)
- [Do GANs leave artificial fingerprints?](https://mlsanity.com/paper/1812.11842/) (2018)
- [DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models](https://mlsanity.com/paper/2210.06998/) (2022)
- [Low-Rank Few-Shot Adaptation of Vision-Language Models](https://mlsanity.com/paper/2405.18541/) (2024)
- [Imagen 3](https://mlsanity.com/paper/2408.07009/) (2024)
- [Source Generator Attribution via Inversion](https://mlsanity.com/paper/1905.02259/) (2019)
- [Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data](https://mlsanity.com/paper/2406.13843/) (2024)
- [Are CLIP features all you need for Universal Synthetic Image Origin Attribution?](https://mlsanity.com/paper/2408.09153/) (2024)
- [Text-to-Image Synthesis: A Decade Survey](https://mlsanity.com/paper/2411.16164/) (2024)
- [When Synthetic Traces Hide Real Content: Analysis of Stable Diffusion Image Laundering](https://mlsanity.com/paper/2407.10736/) (2024)

## Built on by (most cited first, 3 of 3)

- [Guess the Unified Model: How Much Can We Recover from Generated Images?](https://mlsanity.com/paper/2605.25254/) (2026)
- [The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples](https://mlsanity.com/paper/2606.26207/) (2026)
- [Representation and Reference Selection in Training-Free Synthetic Image Attribution](https://mlsanity.com/paper/2607.12052/) (2026)

## Abstract (arXiv)

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.