An illustration to secured way of data mining using privacy preserving data mining

Abstract

The aim of data mining is to extract useful information from huge source of multiple data. But during the process of data mining, intentionally or unintentionally the data becomes visible and thus vulnerable while handling. Privacy Preserving is a new concept in the area of data mining taking the security issues of users’ data being mined as prime concern. It ensures that privacy of sensitive data will be preserved even after mining by multiple parties. There are various existing methods for privacy preserving data mining which are based on data distortion, clustering, intersection, data distribution etc. The paper discusses few of such privacy preserving data mining techniques. At the end of the paper, a simple mathematical approach for this, is also discussed which is applicable for a number of sites, sharing data on distributed database environment.

Keywords:

• Association Rules
• Clustering
• Data Distortion
• Data Mining
• Decision Tree
• Privacy Preservation

Mathematics Subject Classification 2010:

• 68M99