Research On Privacy Protection Method Of Data Release Based On K-anonymous Technology

In recent years,with the rapid development of the Internet and Information technology,people can more easily extract unknown,hidden and potentially valuable information from the data,it leads to the problem that the sensitive privacy data leakage in the process of data release.The sensitive privacy protection has been paid more and more attention in the process of data release.Anonymous privacy protection technology has become a research topic in the field of database and information security,which has aroused widespread concern in industry and academia.The most popular anonymous privacy protection technology is the K-anonymous technology,and it is also used in the process of data release.The thesis mainly studies the anonymous model and anonymity algorithm of anonymous privacy protection technology.For the diversity of sensitive attributes and the execution efficiency of algorithm,two improved algorithms are given.The availability and effectiveness of the two algorithms are verified by experiments.The main research work and achievements of the thesis are as follows:1.The thesis analyzes the current situation of sensitive privacy protection and the commonly used privacy protection technology,and studies the basic K-anonymous model.There is a problem with the model that the sensitive attribute values in the equivalence class after division may be similar,resulting that post-release anonymous data tables may be subject to homogeneous attacks,causing privacy leaks.Based on the basic K-anonymous model,the thesis adds a sensitive privacy protection degree parameter to set up the sensitivity degree of the sensitive attributes,so that the sensitive attribute values in the equivalence class after division maintain diversity.2.On the premise of the definitive model,the thesis introduces a sensitive privacy protection degree parameter to ensure the diversity of sensitive attributes in the equivalence class after division.On the basis of the local generalization algorithm KACA,and the first improved algorithm based on sensitive privacy protection degree(S-KACA algorithm)is given,which improves the diversity of sensitive attributes in the equivalence class after division and prevents privacy disclosure by introducing the sensitive privacy protection degree.3.The improved algorithm S-KACA needs to merge equivalence classes after division whose sensitive attribute values are similar,the data generalization and distance calculation are increased,which leads to the decrease of the execution efficiency of the algorithm,and does not apply to the large-scale data set.Thus,the second improved algorithm based on optimized S-KACA algorithm(K-prototypes-SKACA algorithm)is given.Firstly,the algorithm preprocesses the data set through the clustering algorithm,then anonymizes the data set.It effectively reduces the data generalization and distance calculation,and improves the efficiency of the algorithm.4.The improved algorithms among the algorithm runtime,the amount of information loss,the risk of privacy leakage,and the scalability of the algorithm are compared and analyzed to fully explain the availability,effectiveness and superiority of the improved algorithms.And the improved algorithm is applied to the data set of the e-commerce system to realize the protection function of the user sensitive privacy data.