Journal of Computer, Internet and Network Security ISSN: 2457-0176 (Online)

Authors:-P Srinivasa Rao , N Sushma Rani

Abstract:-Preservation of privacy in data mining is an absolute need for exchanging sensitive information in terms of data analysis and publishing. Threats such as internet phishing posed severe threat on widespread sensitive information over the web. There are some widely used privacy preserving data mining techniques such as association rule mining, clustering and classification based privacy preservation, and k-anonymity. A multi-partition scalable k-anonymization (MSKA) approach using MapReduce [1] is proposed in this paper that targets the scalability issue in Privacy Preserving Data Publishing (PPDP). The proposed approach uses Hadoop’s MapReduce to increase the performance and reduce the runtime of the algorithm for anonymizing the data