English(EN) Differentially Private Datastore Generation for Retrieval-Augmented Inference

新方法为AI推理生成私有数据存储

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-31 19:18

研究人员开发了一个新的差分隐私数据存储生成框架，这对于使用检索增强推理的AI系统至关重要。他们基于哈希的方法对数据进行分区并添加校准噪声，以确保个人隐私同时保持效用。实验表明，在epsilon=5时，准确率仅下降2.6%，并且该方法显著降低了成员推理攻击的有效性。 AI

影响能够安全地发布用于AI的数据存储，可能增加对设备上AI系统的信任和采用。

排序理由这是一篇详细介绍差分隐私数据存储生成新方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 这是一篇详细介绍差分隐私数据存储生成新方法的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
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: 130 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Abdelrahman Abouelenein, Marwan Torki · 2026-06-02 04:00

用于检索增强推理的差分隐私数据存储生成

arXiv:2606.01413v1 Announce Type: cross Abstract: It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datastores without compromising individual privacy. This can be achieved using Differential Privacy (DP), which provides…
arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Marwan Torki · 2026-05-31 19:18

用于检索增强推理的差分隐私数据存储生成

It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datastores without compromising individual privacy. This can be achieved using Differential Privacy (DP), which provides a formal guarantee that ensures individual contri…