Abstract: People today are very reluctant to share their information as they are well aware of the privacy threats of their sensitive data. Data in its original form contains sensitive information about individuals, and publishing such data without revealing sensitive information is a difficult task. The major risk is of those non-sensitive data which may deliver sensitive information indirectly. Privacy preserving data mining (PPDM) try to overcome this problem by protecting the privacy of data without sacrificing the integrity of data. A number of techniques have been proposed for privacy-preserving data mining. This paper provides a review of different approaches for privacy preserving data mining along with merits and demerits. It provides a brief explanation of anonymization approach along with its different techniques like k-anonymity, l-diversity and t-closeness. It also includes comparison between different algorithms of anonymization with their advantages and disadvantages.

Keywords: Privacy preserving, Anonymization, Randomization, Sensitive attributes, k-anonymity.