An analysis of privacy preservation techniques in data mining

Abstract

Data mining techniques are used extensively for deducting the implicit, previously unknown, and potentially useful information from large data sets by using statistical and intelligent methodologies. The deduction of patterns or conclusions may uncover the information that may sometimes compromise the confidentiality and privacy obligations. Preservation of privacy is an important aspect of data mining and thus study of achieving some data mining goals without sacrificing the privacy of the individuals is not only demanding but also a task of practical importance. The analysis of privacy preserving data mining (PPDM) algorithms should consider the effects of these algorithms in mining the results as well as in preserving privacy. The privacy should be preserved in all the three aspects of mining as association rules, classifiers and clusters. In this paper we present a review of the commonly existing efficient methodologies in the context of privacy preservation in data mining.