Data Privacy for Big Data Publishing Using Newly Enhanced PASS Data Mining Mechanism

Abstract

Anonymization is one of the main techniques that is being used in recent times to prevent privacy breaches on the published data; one such anonymization technique is k-anonymiz-ation technique. The anonymization is a parametric anonymization technique used for data anonymization. The aim of the k-anonymization is to generalize the tuples in a way that it cannot be identified using quasi-identifiers. In the past few years, we saw a tremendous growth in data that ultimately led to the concept of the big data. The growth in data made anonymization using conventional processing methods inefficient. To make the anonymi- zation more efficient, we used the proposed PASS mechanism in Hadoop framework to reduce the processing time of anonymization. In this work, we have divided the whole program into the map and reduce part. Moreover, the data types used in Hadoop provide better serialization and transport of data. We performed our experiments on the large dataset. The results proved the best efficiency of our implementation.