PRIVACY PRESERVING DATA MINING SURVEY OF CLASSIFICATIONS

With the rapid progress of data mining, protecting sensitive information is a critical issue before sharing to outside parties. Association rules become a powerful tool in discovering hidden sensitive information among parties, whereas some of them try to protect their own sensitive information by blocking inference channels. Consider two parties who are selling same products in different markets. After sharing their sale information to each other, one tries to mine the data and analyze the adversary’s sale information. After analyzing and accessing beneficial information, the party changes the arrangement of his products in his market since it helps the customer access products more easily and quickly. This results in an increase in the rate of selling in his market by mining the censored data. This paper discusses various methods and techniques used to hide sensitive information before sharing. We have also proposed an algorithm for privacy preserving data mining.

Data Mining; Privacy Preserving Data Mining; Censor Sensitive Information; Association Rules