Maintaining Data Utility While Preserving Privacy In Data Publishing (T-0739) (MFN 6883)

Abstract

Different organizations have individual's sensitive data growing exponentially day by day. Which can be shared among scholars for research purposes. To make sure the privacy of individual's sensitive information while publishing data is a major task. A lot of research work have been done in the field of data publishing. Utility of data is an important subject when high privacy is ensured. To restraint the belief of adversary deducing a sensitive value of victim and achieving sound semantic privacy, one can publish generalized sample of original data so that adversary has low confidence of extrapolation. However if sampled data did not assure full representation of original data then utility of data will suffer. We proposed a technique that combine Stratified sampling with generalization to achieve a sound semantic privacy preserving framework with high data utility. Stratified sampling gives better sample of original data which contain representation of data from each strata of given data set. Experimental results showed that our algorithm provide more accurate data utility as well as privacy as compared to earlier approaches that use generalization and sampling combination.