基于改进贝叶斯网络的高维数据本地差分隐私方法  

Method of Local Differential Privacy Method for High-Dimensional Data Based on Improved Bayesian Network

作　　者：赵佳[1,2] 高塔[1,2] 张建成 ZHAO Jia;GAO Ta;ZHANG Jiancheng(Beijing Key Laboratory of Security and Privacy in Intelligent Transportation,Beijing Jiaotong University,Beijing 100044,China;School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China;Shandong Computer Science Center,Jinan 250014,China;Shandong Zhengzhong Information Technology Co.,Ltd.,Jinan 250014,China)

机构地区：[1]北京交通大学智能交通数据安全与隐私保护北京市重点实验室,北京100044 [2]北京交通大学计算机与信息技术学院,北京100044 [3]山东省计算中心,济南250014 [4]山东正中信息技术股份有限公司,济南250014

出　　处：《信息网络安全》2023年第2期19-25,共7页Netinfo Security

基　　金：国家自然科学基金青年科学基金[61502030];中央高校基本科研业务费[2018JBM016];山东省重大科技创新工程项目[2019JZZY020128]。

摘　　要：文章提出一种基于改进贝叶斯网络的高维数据本地差分隐私方法,首先通过数据源差分隐私保护算法对用户端数据集进行扰动,生成扰动数据集,保护本地原始数据集隐私;然后通过改进的贝叶斯网络将高维数据集降维为多个低维属性集合;最后合成新数据集,使用人工蜂群算法对贝叶斯网络结构进一步改进。实验结果表明,该方法在数据实用性方面具有优势,且得到的贝叶斯网络收敛性更好。In this paper,a local differential privacy method for high-dimensional data based on improved Bayesian network was proposed.By using the differential privacy protection algorithm of data source,the client data set was disturbed to generate the disturbed data set,so that the privacy of the local original data set was protected,and the privacy security of users was fundamentally protected.Then the high-dimensional data set was reduced to several low-dimensional attribute sets by the improved Bayesian network,and the new data set was finally synthesized,and the artificial bee colony algorithm was used to further improve the construction of Bayesian network structure.Finally,the experimental results show that the research method in this paper has advantages in data practicability,and the Bayesian network structure achieved better convergence.

关 键 词：本地差分隐私 贝叶斯网络 人工蜂群算法 高维数据 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]