Privacy-preserving SVM using nonlinear kernels on horizontally partitioned data
Privacy-preserving SVM using nonlinear kernels on horizontally partitioned data
复制标题
DOI：
10.1145/1141277.1141415
复制
发表时间：
2006-04
期刊：
影响因子：
--
通讯作者：
Hwanjo Yu;Xiaoqian Jiang;Jaideep Vaidya
中科院分区：
文献类型：
--
作者：
Hwanjo Yu;Xiaoqian Jiang;Jaideep Vaidya
传统的数据挖掘和知识发现算法假设可以自由访问数据，无论是在集中位置还是以联邦形式。越来越多的隐私和安全问题限制了这种访问，从而使数据挖掘项目脱轨。我们需要的是对这个问题敏感的分布式知识发现。关键是要获得有效的结果，同时保证不泄露数据。支持向量机分类是数据挖掘和机器学习中应用最广泛的分类方法之一。它有着坚实的理论基础和广泛的实际应用。提出了一种隐私保护的支持向量机（SVM）分类方法，简称PP-SVM。我们的解决方案从分布在多方的数据中构建全局SVM分类模型，而不向其他方公开每一方的数据。我们假设数据是水平分区的--每一方都为不同的数据对象收集相同的信息特征。我们量化了所提出的方法的安全性和效率，并强调了未来的挑战。
Traditional Data Mining and Knowledge Discovery algorithms assume free access to data, either at a centralized location or in federated form. Increasingly, privacy and security concerns restrict this access, thus derailing data mining projects. What we need is distributed knowledge discovery that is sensitive to this problem. The key is to obtain valid results, while providing guarantees on the non-disclosure of data. Support vector machine classification is one of the most widely used classification methodologies in data mining and machine learning. It is based on solid theoretical foundations and has wide practical application. This paper proposes a privacy-preserving solution for support vector machine (SVM) classification, PP-SVM for short. Our solution constructs the global SVM classification model from the data distributed at multiple parties, without disclosing the data of each party to others. We assume that data is horizontally partitioned -- each party collects the same features of information for different data objects. We quantify the security and efficiency of the proposed method, and highlight future challenges.