Metraipolis › archive › dc_a84cd5e55c53

Differentially Private and Fairness-Audited Score Diffusion for Irregular Longitudinal Health Records — arXiv:2609.22401

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22401
License (as archived)
CC0-1.0
Archived
2026-10-09T07:00:51.818Z
SHA-256 of the archived text
3fdfb0c372a123a4e7ea062248627bd5f5e0a2029d7b90f7e69b2cc15da1e7c2
Stable URL of this page
https://metraipolis.com/documento/dc_a84cd5e55c53

How to cite

Differentially Private and Fairness-Audited Score Diffusion for Irregular Longitudinal Health Records — arXiv:2609.22401 — arXiv (en), https://arxiv.org/abs/2609.22401 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a84cd5e55c53 (Metraipolis archive dc_a84cd5e55c53, sha256 3fdfb0c372a123a4e7ea062248627bd5f5e0a2029d7b90f7e69b2cc15da1e7c2)
BibTeX
@misc{dca84cd5e55c53,
  title = {Differentially Private and Fairness-Audited Score Diffusion for Irregular Longitudinal Health Records — arXiv:2609.22401},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22401},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a84cd5e55c53; sha256 3fdfb0c372a123a4e7ea062248627bd5f5e0a2029d7b90f7e69b2cc15da1e7c2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22401. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sharing irregular longitudinal health records can accelerate model development, yet synthetic releases may leak participation, distort temporal dependence, suppress rare events, or reduce utility for underrepresented groups. We present TRUST LONGSYNTH, an auditable patient level private generator that combines bounded sufficient statistics, zCDP accounted Gaussian releases, conditional analytic score diffusion, block banded temporal covariance, separate missingness and gap models, and a protected event sampling floor with population weights. The method was evaluated on five independently generated, three cohort benchmarks containing 720 patients, fourteen irregular observation slots, six mixed variables, informative missingness, and a rare deterioration outcome. At epsilon = 12 and delta = 10 to the power of minus 5, TRUST LONGSYNTH achieved mean train synthetic test real AUPRC 0.342, Brier score 0.088, expected calibration error 0.082, correlation error 0.222, autocorrelation error 0.317, and membership attack AUROC 0.499. Relative to the private diagonal score baseline, AUPRC increased by 7.5 percent, while Brier, calibration, correlation, and autocorrelation errors decreased by 6.1 percent, 17.0 percent, 28.0 percent, and 30.1 percent, respectively. The method did not dominate every nonprivate or discrete baseline, and corrected paired tests were inconclusive with five seeds. Canary exposure was 1.8 percent, compared with 28.8 percent for DP Score in the same stress test. These findings support a transparent privacy utility fairness evaluation protocol, not clinical validity or unconditional release safety, and motivate governed external validation on real multi site records.

Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2609.22401 — 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 2026-10-09T06:56:00.940Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).