English(EN) Subgroup Membership Inference Audits of Differentially Private Synthetic Text

差分隐私在合成文本发布中未能保护弱势子群

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-11 04:00

对差分隐私合成文本发布的新审计显示，虽然差分隐私（DP）能有效减少平均成员推断泄露，但它对某些记录的保护程度不成比例。该研究定义了一个子群目标成员推断博弈来量化这种风险，表明合成发布仍然可能泄露子群成员身份。研究还强调，泄露信息的具体记录取决于所使用的发布机制，而不仅仅是记录本身。 AI

影响强调了合成数据生成中潜在的隐私风险，敦促在部署基于此类数据训练的模型时要谨慎。

排序理由学术论文，详细介绍了差分隐私合成文本的新审计方法和发现。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了差分隐私合成文本的新审计方法和发现。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar, Siew Kei Lam, Anil Anthony Bharath · 2026-09-11 04:00

差分隐私合成文本的子群组成员身份推断审计

arXiv:2609.09848v1 Announce Type: cross Abstract: 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…