计算机工程与应用 ›› 2020, Vol. 56 ›› Issue (5): 80-84.DOI: 10.3778/j.issn.1002-8331.1812-0152

• 大数据与云计算 • 上一篇    下一篇

基于聚类的云隐私行为挖掘技术

王杰,陈志刚,刘加玲,程宏兵   

  1. 1.中南大学 计算机学院,长沙 410012
    2.衡阳师范学院 计算机科学与技术学院,湖南 衡阳 421002
    3.浙江工业大学 计算机科学与技术学院,杭州 310023
  • 出版日期:2020-03-01 发布日期:2020-03-06

Privacy Behavior Mining Technology for Cloud Computing Based on Clustering

WANG Jie, CHEN Zhigang, LIU Jialing, CHENG Hongbing   

  1. 1.School of Computer Science & Engineering, Central South University, Changsha 410012, China
    2.College of Computer Science & Technology, Hengyang Normal College, Hengyang, Hunan 421002, China
    3.College of Computer Science & Technology, Zhejiang University of Technology, Hangzhou 310023, China
  • Online:2020-03-01 Published:2020-03-06

摘要:

随着云计算的不断普及,隐私安全问题逐渐显现,已成为制约云计算发展的重要障碍。受经济社会“问责制”的启发,从规范和约束云参与者隐私行为的角度,针对云参与者的隐私违约认定的问题,进行了基于审查对象隐私行为挖掘的研究。对隐私日志行为数据进行预处理,采用夹角余弦法来定义任意两个隐私会话之间的相似度并构建云隐私间的相似度矩阵,选择K-均值聚类算法对隐私会话基于设置的云隐私规则进行相似度聚类。实验测试结果表明所提出的隐私聚类挖掘技术能够精确地对云系统隐私行为及其相似度进行识别并聚类。

关键词: 云计算, 隐私保护, 聚类, 数据挖掘

Abstract:

With the continuous popularity of cloud computing, privacy and security issues have gradually emerged, which has become an important factor restricting the development of cloud computing. Inspired by the economic and social “accountability system”, this paper, from the perspective of regulating and restricting the privacy behavior of cloud partici-pants, aims at the identification of privacy breach of contract of cloud participants, conducts a research based on the mining of privacy behavior of censors. Firstly, the data of privacy log behavior are preprocessed, then the similarity between any two privacy sessions is defined by the angle cosine method, and the similarity matrix between cloud privacy is constructed. Finally, it chooses K-means clustering algorithm to cluster the similarity of privacy sessions based on the set cloud privacy rules. Experimental results show that the proposed privacy clustering mining technology can accurately identify and cluster the privacy behavior similarity of cloud systems.

Key words: cloud computing, privacy-preserving, clustering, data mining