基于安全多方计算的隐私保护聚类挖掘
Privacy preserving clustering mining based on secure multiparty computation
针对聚类挖掘过程中的数据隐私泄露问题，本文将安全多方计算协议和K-Means聚类算法相结合，设计了一种数据水平分布下的用户隐私保护聚类模型，保证了多方参与下数据的保密性，同时不会对数据的挖掘结果产生较大影响。在UCI数据集上的实验结果表明，该算法模型能够在保护用户数据隐私的前提下，提供了有效、准确的挖掘结果。
For the loss of privacy exits in the process of data mining, we combine secure multiparty computation and K-Means clustering algorithm to design a model which can protect data privacy under the horizontal distribution, the model can ensure the confidentiality of data under multi-stakeholder involvement, and will not have a greater impact on the results of data mining. Experimental results on UCI datasets show that the algorithm is able to protect the privacy of user data, while providing efficient and accurate mining results.
单家伟、刘念
计算技术、计算机技术
信息安全聚类挖掘隐私保护安全多方计算K-Means聚类UCI数据集
clustering miningprivacy protectionsecure multiparty computationK-Means clusteringUCI datasets
单家伟,刘念.基于安全多方计算的隐私保护聚类挖掘[EB/OL].(2014-08-08)[2025-08-23].http://www.paper.edu.cn/releasepaper/content/201408-79.点此复制
评论