Metraipolis › archive › dc_df78fbb73e79

Automated screening of privacy risks in medical AI — arXiv:2610.30229

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.30229
License (as archived): CC0-1.0
Archived: 2026-10-23T15:14:47.642Z
SHA-256 of the archived text: b8fc832823cf681872a146a12100197d8ef01b7a1a268aae299aa532d5369e4a
Stable URL of this page: https://metraipolis.com/documento/dc_df78fbb73e79

How to cite

Automated screening of privacy risks in medical AI — arXiv:2610.30229 — arXiv (en), https://arxiv.org/abs/2610.30229 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df78fbb73e79 (Metraipolis archive dc_df78fbb73e79, sha256 b8fc832823cf681872a146a12100197d8ef01b7a1a268aae299aa532d5369e4a)

BibTeX

@misc{dcdf78fbb73e79,
  title = {Automated screening of privacy risks in medical AI — arXiv:2610.30229},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.30229},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df78fbb73e79; sha256 b8fc832823cf681872a146a12100197d8ef01b7a1a268aae299aa532d5369e4a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30229. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the patients who contributed them. However, a model can reveal whether a patient's records were used in training, a privacy breach known as a membership inference attack. This risk is usually reported as a cohort average, which can appear negligible while individual patients are almost certainly exposed. Identifying potentially vulnerable records before developing a production model could make privacy assessment more practical. We measured each patient's vulnerability to membership inference attack, across 7,789 models trained on six clinical datasets in four modalities, including two adapted pretrained medical models. Training choices changed how many patients had high attack scores, but the patients who ranked highest by risk largely stayed the same across the configurations we tested. Stronger weight decay reduced the exposed cohort up to threefold, yet largely the same patients remained most at risk across training recipes, architectures and initializations, including foundation models. Therefore, we developed a lightweight screening tool that uses four small models to identify patients with high risk of exposure before production-model training. We also assessed if flagged patients could be protected without removing their data. Privacy screening should become incorporated into data preparation for clinical AI.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.30229 — 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 2026-10-23T15:09:08.499Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).