Data Perturbation Method for Privacy Preseving Data Mining Based On Z-Score

Main Article Content

Santosh Kumar Bhandare


Data mining system consist of large amount of private and sensitive data such as healthcare, financial and criminal records. Some or all information of database may be confidential. This confidential information of database cannot be share to every one, so privacy protection of confidential information is required in data mining system for avoiding privacy leakage of data. Data perturbation is one of the best methods for privacy preserving data mining. In this paper we used data perturbation method for preserving privacy as well as accuracy. In data perturbation method individual data value are distorted before data mining application. In this paper we present Z- Score normalization transformation based data perturbation. The privacy parameters are used for measurement of privacy protection and the utility measure shows the performance of data mining technique after data distortion. We conducted experiment on real life dataset and the result show that Z-Score normalization transformation based data perturbation method is effective to protect confidential information and also maintain the performance of data mining technique after data distortion.



Keywords: Privacy preserving, normalization, data perturbation, classification, data mining


Download data is not yet available.

Article Details