arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.03552cs.LGcs.CR
收藏

从多方数据中私下学习

Learning Privately from Multiparty Data

The Ohio State University(俄亥俄州立大学);University of California, San Diego(加州大学圣地亚哥分校)

Jihun Hamm, Paul Cao, Mikhail Belkin

摘要:

从多方收集的私有数据中学习分类器是一个重要的问题,具有许多潜在的应用。我们如何在不访问任何一方的私有数据的情况下,通过组合来自不同方的本地训练的分类器来构建一个准确的、有差异的私有全局分类器?我们建议通过首先从辅助未标记数据创建标记数据,然后训练全球$ε$差分私有分类器来转移本地分类器集成的“知识”。我们表明,多数表决是过于敏感,因此提出了一个新的风险加权类概率估计的合奏。相对于非私有解,我们的私有解具有由$O(ε^{-2}M^{-2})$限定的泛化误差,其中$M$是参与方的数量。当$M$较大时,例如在人群感知应用中,这允许强隐私而不损失性能。我们展示了我们的方法与现实的任务活动识别,网络入侵检测和恶意URL检测的性能。

英文摘要:

Learning a classifier from private data collected by multiple parties is an important problem that has many potential applications. How can we build an accurate and differentially private global classifier by combining locally-trained classifiers from different parties, without access to any party's private data? We propose to transfer the `knowledge' of the local classifier ensemble by first creating labeled data from auxiliary unlabeled data, and then train a global $ε$-differentially private classifier. We show that majority voting is too sensitive and therefore propose a new risk weighted by class probabilities estimated from the ensemble. Relative to a non-private solution, our private solution has a generalization error bounded by $O(ε^{-2}M^{-2})$ where $M$ is the number of parties. This allows strong privacy without performance loss when $M$ is large, such as in crowdsensing applications. We demonstrate the performance of our method with realistic tasks of activity recognition, network intrusion detection, and malicious URL detection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑