Metraipolis › archive › dc_25e1db92aca6

Probing Local Conditional Fit for Diffusion Model Membership Inference — arXiv:2611.02578

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02578
License (as archived): CC0-1.0
Archived: 2026-11-03T10:23:49.167Z
SHA-256 of the archived text: 1bd20a1ccdfd342eb6b3b00f38a6ddaf132bd55929294d91181b4a114ccf9379
Stable URL of this page: https://metraipolis.com/documento/dc_25e1db92aca6

How to cite

Probing Local Conditional Fit for Diffusion Model Membership Inference — arXiv:2611.02578 — arXiv (en), https://arxiv.org/abs/2611.02578 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_25e1db92aca6 (Metraipolis archive dc_25e1db92aca6, sha256 1bd20a1ccdfd342eb6b3b00f38a6ddaf132bd55929294d91181b4a114ccf9379)

BibTeX

@misc{dc25e1db92aca6,
  title = {Probing Local Conditional Fit for Diffusion Model Membership Inference — arXiv:2611.02578},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02578},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_25e1db92aca6; sha256 1bd20a1ccdfd342eb6b3b00f38a6ddaf132bd55929294d91181b4a114ccf9379},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02578. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Membership inference determines whether a candidate example was used to train a text-to-image diffusion model and is an important tool for auditing training-data use. We identify a directional membership signal in \emph{conditional prediction shifts}, the changes in predicted noise under alternative text conditions at a fixed noisy input: whether movement toward the alternative prediction initially lowers or raises the denoising loss from its value under the original caption. Members exhibit less room for such local improvement. To quantify this response, we propose \emph{LoFIT} (Local Conditional Fit), which measures the initial response of the denoising loss along normalized prediction shifts and aggregates it across multiple text conditions and diffusion states. LoFIT requires no target-model gradients and can be computed using only forward queries to the denoiser. Evaluations on four datasets show improved membership discrimination across fine-tuned and pretrained models. LoFIT distinguishes members early in fine-tuning, while the naive denoising-loss baseline remains near chance. Controlled comparisons show that the membership signal is concentrated in the first-order response, with little discrimination from prediction-shift magnitude alone.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02578 — 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 2026-11-03T10:19:49.885Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).