基于本地差分隐私的BIRCH混合数据算法  

BIRCH Mixed Data Algorithm Based on Local Differential Privacy

作　　者：王豪石 张淑芬 董燕灵 徐超 WANG Hao-shi;ZHANG Shu-fen;DONG Yan-ling;XU Chao(College of Science,North China University of Science and Technology,Tangshan Hebei 063210,China;Hebei Key Laboratory of Data Science and Application,Tangshan Hebei 063210,China;Tangshan Key Laboratory of Data Science,Tangshan Hebei 063210,China)

机构地区：[1]华北理工大学理学院,河北唐山063210 [2]河北省数据科学与应用重点实验室,河北唐山063210 [3]唐山市数据科学重点实验室,河北唐山063210

出　　处：《华北理工大学学报（自然科学版）》2023年第1期89-98,共10页Journal of North China University of Science and Technology：Natural Science Edition

基　　金：国家自然科学基金项目(U20A20179)。

摘　　要：BIRCH算法是一种适合处理大规模数值型的聚类算法,但现实生活中的数据往往是混合型数据,导致了BIRCH算法的局限性;此外,在使用BIRCH算法进行聚类分析的过程中存在隐私泄露的风险,而传统的中心化差分隐私算法存在需要可信第三方的缺点。针对以上缺陷,提出了基于本地差分隐私的BIRCH混合数据(LDP-BIRCH)算法,对混合型数据中的非数值型数据进行编码处理,并使用本地差分隐私对数据集进行扰动,将扰动后的数据集发给第三方进行BIRCH算法聚类分析。研究结果表明,LDP-BIRCH算法在adult和Facebook Live Sellers in Thailand数据集上满足隐私保护性和聚类可用性。BIRCH algorithm is a kind of clustering algorithm suitable for processing large-scale numerical types,but the data in real life are often mixed data,which results in the limitation of BIRCH algorithm.In addition,there is a risk of privacy disclosure in the process of using BIRCH algorithm for cluster analysis,while the traditional centralized differential privacy algorithm has the disadvantage of requiring a trusted third party.Aiming at the above defects,BIRCH mixed data algorithm based on local differential privacy(LDP-BIRCH)was proposed.Non-numerical data in the mixed data was coded,and the data set was disturbed by local differential privacy.The disturbed data set was sent to a third party for cluster analysis.The research results show that,LDP-BIRCH algorithm meets privacy protection and cluster availability on adult and Facebook Live Sellers in Thailand data set.

关 键 词：本地差分隐私 BIRCH算法 混合数据 随机响应机制 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]