A new model for privacy preserving sensitive Data Mining

Data Mining and Knowledge Discovery is an indispensable technology for business and researches in many fields such as statistics, machine learning, pattern recognition, databases and high performance computing. In which Privacy Preserving Data Mining has the potential to increase the reach and benefits of data mining technology. This allows publishing a microdata without disclosing private information. Publishing data about individuals without revealing sensitive information about them is an important problem. k-anonymity and l-Diversity has been proposed as a mechanism for protecting privacy in microdata publishing. But both the mechanisms are insufficient to protect the privacy issues like Homogeneity attack, Skewness Attack, Similarity attack and Background Knowledge Attack. A new privacy measure called “(n, t)-proximity” is proposed which is more flexible model. Here first introduction about data mining is presented, and then research challenges are given. Followed by privacy preservation measures and problems with k-anonymity and l-Diversity are discussed. The rest of the paper is organised as (n, t)-proximity model, experimental results and analysis followed by conclusion.

1 Introduction

Data mining is the process of posing queries and extracting useful patterns or trends, often previously unknown, from large amount of data. This Data mining process is carried out using various techniques such as those form pattern recognition and machine learning. Today the technology is being used for a wide variety of application, from marketing and finance to medicine and biotechnology to multimedia and entertainment. In recent there has been interest in using data mining for privacy and counter terrorism.