cs.CVNov 4, 2026

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

Authors: Ashutosh Dayal, Mallika Garg, Debashis Sen

Organizations: Indian Institute of Technology Kharagpur, INDIA

Abstract

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 140140K-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 https://github.com/mallikagarg/IntrAA-SD.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Diffusion Model Attribution via Spectral Coupling of Denoiser Responses

    Jun 26, 2026Pragati Shuddhodhan Meshram, Varun ChandrasekaranDiffusion Models

  2. DNA: Dual-stage Native Attribution for Generated Image Source Tracing

    Jul 15, 2026Chao Wang, Kejiang Chen, Zijin Yang +4Digital Image ForensicsAI-Generated Image Detection

  3. IncreFA: Breaking the Static Wall of Generative Model Attribution

    Apr 20, 2026Haotian Qin, Dongliang Chang, Yueying Gao +3Continual LearningOpen-Set Recognition