The Most Prominent Technique for Privacy Preservation in Mining Micro Data (NCCC-13)

Abstract

The data are increasingly being collected and used. Privacy preserving data
mining tries to strike a balance between two opposing forces: the objective of discovering
valuable information and knowledge, verse the responsibility of protecting individual’s
privacy. Several anonymization techniques, such as generalization and bucketization, have
been designed for preserving privacy in micro data publishing. But generalization loses
considerable amount of data. On the other side, bucketization does not prevent
membership disclosure and there is no clear isolation of quasi identifiers and sensitive
attributes. We present a novel data anonymization technique called slicing which partitions
the data both horizontally and vertically. Our empirical result shows that slicing protects
individual entity with high degree of data utility than generalization and suppression.
Slicing also provides attribute and membership disclosure protection. And our algorithm
satisfies ℓ-diverse requirement.