Metraipolis › archive › dc_bbc1eee34500

Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline — arXiv:2611.06000

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06000
License (as archived)
CC0-1.0
Archived
2026-11-05T18:17:41.339Z
SHA-256 of the archived text
3d06d9bde709b7446e49b129531b9395913dea02d83d879a853bec5f797359e2
Stable URL of this page
https://metraipolis.com/documento/dc_bbc1eee34500

How to cite

Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline — arXiv:2611.06000 — arXiv (en), https://arxiv.org/abs/2611.06000 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbc1eee34500 (Metraipolis archive dc_bbc1eee34500, sha256 3d06d9bde709b7446e49b129531b9395913dea02d83d879a853bec5f797359e2)
BibTeX
@misc{dcbbc1eee34500,
  title = {Intra-Architecture Source Attribution for Stable Diffusion: A New Task with Benchmark Dataset and Baseline — arXiv:2611.06000},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06000},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbc1eee34500; sha256 3d06d9bde709b7446e49b129531b9395913dea02d83d879a853bec5f797359e2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06000. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Designing systems that attribute a generated image to its source model has lately become a major area of AI research. Most existing datasets and systems related to image source attribution are targeted towards the detection of architectural signatures of the source models. Distinct from this, focusing on stable diffusion, we introduce a novel task, IntrAA-SD, Intra-Architecture source Attribution for Stable Diffusion, where the source models to be differentiated share the same architectural backbone and differ only due to fine-tuning. The proposed task aligns with the emergence of fine-tuned generators having the same architecture, like Juggernaut XL and RealVis XL, which are fine-tuned versions of Stable Diffusion XL (SDXL). We provide a first-of-its-kind $140$K-image benchmark dataset containing images generated from different fine-tunes of SDXL, along with in-domain and out-of-distribution prompts. We also provide a baseline framework for IntrAA-SD, which leverages a style-conditioned Mixture-of-Experts network. It uses a frozen CLIP backbone to capture the image style and gate the MoE, which processes fine-tuned trace features from a high-resolution LoRA-adapted DINOv2 network. The fine-tuned models used, the prompting strategies considered, and the formation details employed in the novel dataset are elaborated. Our baseline intra-architecture source attribution method is evaluated in terms of attribution accuracy on our dataset, and ablation studies are also performed. Code and dataset is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.06000 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-05T18:12:49.043Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).