[1]谢雅琪,杨庚.多项式回归的差分隐私保护算法[J].计算机技术与发展,2022,32(08):103-109.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 017]
　XIE Ya-qi,YANG Geng.Differential Privacy Preservation in Polynomial Regression Analysis[J].,2022,32(08):103-109.[doi:10. 3969 / j. issn. 1673-629X. 2022. 08. 017]
点击复制

多项式回归的差分隐私保护算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年08期
页码:
103-109
栏目:
网络与安全
出版日期:
2022-08-10

文章信息/Info

Title:
Differential Privacy Preservation in Polynomial Regression Analysis
文章编号:
1673-629X(2022)08-0103-07
作者:
谢雅琪1;  杨庚1; 2
1. 南京邮电大学 计算机学院,江苏 南京 210046;
2. 江苏省大数据安全与智能处理重点实验室,江苏 南京 210023
Author(s):
XIE Ya-qi1; YANG Geng1; 2
1. School of Computer,Nanjing University of Posts and Telecommunications,Nanjing 210046,China;
2. Jiangsu Province Key Laboratory of Big Data Security and Intelligent Processing,Nanjing 210023,China
关键词:
机器学习; 差分隐私; 多项式回归; 数据隐私保护; 隐私预算分配
Keywords:
machine learning; differential privacy; polynomial regression; data privacy preservation; privacy budget allocation
分类号:
TP309
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 08. 017
摘要:
多项式回归是用来确定两种或两种以上变量间相互依赖的非线性定量关系的一种统计分析方法,在大数据分析中有广泛的应用。 通常,挖掘的数据集包含一些敏感属性,在数据挖掘过程和数据发布中,如不加保护会引起隐私泄露。基于对代价函数添加噪声的方法,该文设计了一种满足差分隐私的多项式回归算法 FM-on-PR,并且针对现实应用中的需求,对该算法进行了优化,获得了两种分别对数据安全性和数据可用性进行加强的算法 DPC-on-PR 和 DPBA-on-PR。通过理论证明了它们满足差分隐私性质,并使用多个数据集进行实验仿真,测试算法性能,结果表明了这些方法具有有效性,并且经过对比,得出了其中拟合优度最高的 DPBA-on-PR 算法。
Abstract:
Polynomial regression is used to find out the interdependent nonlinear quantitative relationships between multiple variables inmathematical statistics,which has a wide application in big data analysis. Usually,the dataset contains some sensitive attributes,which cancause privacy leakage without preservation in the data mining and data release. Based on the method of adding noise to the cost function,we design a polynomial regression algorithm FM-on-PR to satisfy the difference privacy. According to the requirements of practical applications,such algorithm is optimized,and two algorithms DPC-on-PR and DPBA-on-PR are obtained to enhance data security and data availability respectively. They are both proven to satisfy the differential privacy property through theory. In addition,simulation is performed with several datasets on these algorithms to test their performance. Results demonstrate the effectiveness of these methods and,after comparison,show DPBA-on-PR has the best goodness of fit.

相似文献/References:

[1]陈全 赵文辉 李洁 江雨燕.选择性集成学习算法的研究[J].计算机技术与发展,2010,(02):87.
　CHEN Quan,ZHAO Wen-hui,LI Jie,et al.Research of Selective Ensemble Learning Algorithm[J].,2010,(08):87.
[2]黄秀丽 王蔚.SVM在非平衡数据集中的应用[J].计算机技术与发展,2009,(06):190.
　HUANG Xiu-li,WANG Wei.Application of SVM in Imbalances Dataset[J].,2009,(08):190.
[3]鲁晓南 接标.一种基于个性化邮件特征的反垃圾邮件系统[J].计算机技术与发展,2009,(08):155.
　LU Xiao-nan,JIE Biao.An Individual Anti- Spam Technology[J].,2009,(08):155.
[4]张苗 张德贤.多类支持向量机文本分类方法[J].计算机技术与发展,2008,(03):139.
　ZHANG Miao,ZHANG De-xian.Research on Text Categorization Based on. M- SVMs[J].,2008,(08):139.
[5]汤萍萍 王红兵.基于强化学习的Web服务组合[J].计算机技术与发展,2008,(03):142.
　TANG Ping-ping,WANG Hong-bing.Web Service Composition Based on Reinforcement -Learning[J].,2008,(08):142.
[6]杨雪洁 赵姝 张燕平.基于商空间理论的冬小麦产量预测和分析[J].计算机技术与发展,2008,(03):249.
　YANG Xue-jie,ZHAO Shu,ZHANG Yan-ping.Analysis on Winter Wheat Yield Based on Quotient Space Theory[J].,2008,(08):249.
[7]汤伟 程家兴 纪霞.一种基于概率推理的邮件过滤系统的研究与设计[J].计算机技术与发展,2008,(08):76.
　TANG Wei,CHENG Jia-xing,JI Xia.Research and Design of a Spam Filtering System Based on Probability Inference[J].,2008,(08):76.
[8]孙海虹 丁华福.基于模糊粗糙集的Web文本分类[J].计算机技术与发展,2010,(07):21.
　SUN Hai-hong,DING Hua-fu.Web Document Classification Based on Fuzzy-Rough Set[J].,2010,(08):21.
[9]汤伟 程家兴 纪霞.统计学理论在邮件分类中的应用研究[J].计算机技术与发展,2008,(12):231.
　TANG Wei,CHENG Jia-xing,JI Xia.Research and Design of a Spam Filtering System Based on Statistical Learning Theory[J].,2008,(08):231.
[10]张高胤 谭成翔 汪海航.基于K-近邻算法的网页自动分类系统的研究及实现[J].计算机技术与发展,2007,(01):21.
　ZHANG Gao-yin,TAN Cheng-xiang,WANG Hai-hang.Design and Implementation of Web Page Automation Classification System Based on K- Nearest Neighbor Algorithm[J].,2007,(08):21.

更新日期/Last Update: 2022-08-10