Metraipolis › archive › dc_63a3ca506e53
Subgroup Membership Inference Audits of Differentially Private Synthetic Text — arXiv:2609.09848
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09848
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:26:28.245Z
- SHA-256 of the archived text
25e2297bf47bb3fa909b00714e634126cee60325a7b69890b9591e6d2198cbf9- Stable URL of this page
https://metraipolis.com/documento/dc_63a3ca506e53
How to cite
Subgroup Membership Inference Audits of Differentially Private Synthetic Text — arXiv:2609.09848 — arXiv (en), https://arxiv.org/abs/2609.09848 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_63a3ca506e53 (Metraipolis archive dc_63a3ca506e53, sha256 25e2297bf47bb3fa909b00714e634126cee60325a7b69890b9591e6d2198cbf9)
BibTeX
@misc{dc63a3ca506e53,
title = {Subgroup Membership Inference Audits of Differentially Private Synthetic Text — arXiv:2609.09848},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09848},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_63a3ca506e53; sha256 25e2297bf47bb3fa909b00714e634126cee60325a7b69890b9591e6d2198cbf9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09848. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Synthetic data releases are increasingly proposed in the literature as a means of sharing realistic data replicas in lieu of sensitive private datasets. Even when the worst-case privacy leakage of such releases is bounded by means of differential privacy (DP), in practice a residual risk remains. Membership inference attack (MIA) audits are conducted to empirically quantify this risk. However, existing methods only measure average-case risk for randomly drawn records, which might conceal the risk to vulnerable subgroups. To highlight this issue, we define a subgroup-targeted membership inference game in which the target pool is an explicit parameter, and instantiate it with an audit of 32 proxies under three scenarios with different levels of attacker knowledge, across four datasets, three generators (DP-SGD fine-tuning, API-based prompting, and activation steering), and five privacy budgets. The audit shows that synthetic releases leak subgroup membership and that prior attacks systematically underestimate this leakage. DP is effective at the aggregate level: it substantially reduces average leakage at every budget we test. Three observations temper this picture. First, the remaining leakage is concentrated rather than spread out: under DP, a tenth of the records carries roughly 40% of it. Second, the protection DP delivers in practice is uneven: within its worst-case guarantee, the noise removes more of the measured leakage from random records than from high-risk ones---and a merged-pool audit that scores both record types against shared negatives confirms this at the record level. Third, \emph{which} records leak proves to be a property of the release mechanism rather than of the record alone, so record-level risk cannot be assessed independently of the release.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.09848 — 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 2026-10-16T07:00:16.354Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).