Italiano(IT) Label Differential Privacy via Aggregation

新方法使用线性聚合实现标签差分隐私

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

研究人员通过对训练实例进行线性聚合，引入了一种实现标签差分隐私（label-DP）的新颖方法。这项技术在最近的一篇arXiv论文中有所介绍，它利用 i.i.d. N(0, 1) 权重来保护敏感的训练标签，同时保持回归任务的效用。与先前的方法相比，所提出的方法通过关注最小线性回归损失而非数据矩阵的最小奇异值，提供了改进的实际界限。该论文还将这些隐私保证扩展到涉及子采样不相交实例包和 Lipschitz 约束的神经网络回归任务的场景。 AI

影响引入了一种增强机器学习模型中数据隐私的新方法，可能会影响敏感训练数据的处理方式。

排序理由关于机器学习中新颖的隐私保护技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

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: 27 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于机器学习中新颖的隐私保护技术的学术论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv stat.ML TIER_1 Italiano(IT) · Anand Brahmbhatt, Rishi Saket, Shreyas Havaldar, Anshul Nasery, Yukti Makhija, Aravindan Raghuveer · 2026-09-11 04:00

通过聚合实现标签差分隐私

arXiv:2310.10092v4 Announce Type: replace-cross Abstract: This paper explores the use of linear aggregation to protect the privacy of sensitive training labels through the concept of \emph{label differential privacy} (label-DP) while maintaining regression task utility. Our key f…

本文如何被排名

报道来源 [1]

通过聚合实现标签差分隐私

相关实体

相关话题