arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.03517cs.CRcs.LG
收藏

具有安全多方计算的隐私保护特征选择

Privacy-Preserving Feature Selection with Secure Multiparty Computation

University of Washington(华盛顿大学);Monash University(莫纳什大学);Ghent University(根特大学)

Xiling Li, Rafael Dowsley, Martine De Cock

摘要:

关于使用安全多方计算(MPC)进行隐私保护机器学习的现有工作几乎完全集中在模型训练和对训练模型的推理上,从而忽略了重要的数据预处理阶段。在这项工作中,我们提出了第一个MPC为基础的协议,私人特征选择的基础上的过滤器的方法,这是独立的模型训练,并可以与任何MPC协议的组合使用排名功能。为此,我们提出了一个有效的特征评分协议的基础上基尼杂质。为了证明我们的方法在实际数据科学中的可行性,我们在常用的机器学习即服务配置中使用所提出的MPC协议进行特征选择实验,其中计算外包给多个服务器,具有半诚实和恶意对手。关于有效性,我们表明,安全的特征选择与建议的协议提高了分类器的准确性,在各种现实世界的数据集,而不会泄露信息的特征值,甚至哪些功能被选中。关于效率,我们记录了从几秒到一小时的运行时间,以完成我们的协议,这取决于数据集的大小和安全设置。

英文摘要:

Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage. In this work, we propose the first MPC based protocol for private feature selection based on the filter method, which is independent of model training, and can be used in combination with any MPC protocol to rank features. We propose an efficient feature scoring protocol based on Gini impurity to this end. To demonstrate the feasibility of our approach for practical data science, we perform experiments with the proposed MPC protocols for feature selection in a commonly used machine-learning-as-a-service configuration where computations are outsourced to multiple servers, with semi-honest and with malicious adversaries. Regarding effectiveness, we show that secure feature selection with the proposed protocols improves the accuracy of classifiers on a variety of real-world data sets, without leaking information about the feature values or even which features were selected. Regarding efficiency, we document runtimes ranging from several seconds to an hour for our protocols to finish, depending on the size of the data set and the security settings.

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。

↑