arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.09679cs.CRcs.LGstat.ML
收藏

协作在具有差分隐私的凸机器学习中的价值

The Value of Collaboration in Convex Machine Learning with Differential Privacy

Macquarie University(麦考瑞大学);CSIRO’s Data61(澳大利亚联邦科学与工业研究组织数据61研究所);The University of Melbourne(墨尔本大学);Australian National University(澳大利亚国立大学)

Nan Wu, Farhad Farokhi, David Smith, Mohamed Ali Kaafar

摘要:

在本文中,我们将机器学习应用于多个数据所有者所拥有的分布式私有数据,这些数据所有者可以访问非重叠的训练数据集。我们使用噪声,差分私有梯度,以最小化随机梯度下降的机器学习模型的适应度成本。我们使用适应度成本来量化训练模型的质量,作为隐私预算和分布式数据集大小的函数,以捕获机器学习中隐私和实用性之间的权衡。通过这种方式,我们可以在执行潜在的计算昂贵的机器学习算法之前预测隐私感知数据所有者之间的协作结果。特别是,我们表明,训练机器学习模型的健身使用差分私人梯度查询和训练的机器模型的健身在没有任何隐私问题之间的差异是成反比的训练数据集的平方和隐私预算的平方的大小。我们成功地验证了所提出的隐私感知学习算法的实际性能的性能预测,适用于:金融数据集,用于确定贷款利率使用回归;和检测信用卡欺诈使用支持向量机。

英文摘要:

In this paper, we apply machine learning to distributed private data owned by multiple data owners, entities with access to non-overlapping training datasets. We use noisy, differentially-private gradients to minimize the fitness cost of the machine learning model using stochastic gradient descent. We quantify the quality of the trained model, using the fitness cost, as a function of privacy budget and size of the distributed datasets to capture the trade-off between privacy and utility in machine learning. This way, we can predict the outcome of collaboration among privacy-aware data owners prior to executing potentially computationally-expensive machine learning algorithms. Particularly, we show that the difference between the fitness of the trained machine learning model using differentially-private gradient queries and the fitness of the trained machine model in the absence of any privacy concerns is inversely proportional to the size of the training datasets squared and the privacy budget squared. We successfully validate the performance prediction with the actual performance of the proposed privacy-aware learning algorithms, applied to: financial datasets for determining interest rates of loans using regression; and detecting credit card frauds using support vector machines.

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。

↑