Perpetuate Data Report based on the Slicing Approach

Anonymization is a technique preserving privacy on micro data, we have so many anonymization techniques like generalization, bucketization all these are privacy preserving on sensitive data, with these techniques there is no security for the data, generalization loses the important data and bucketization is not preventing membership disclosure and does not apply on the data for clear separation in quasi identifiers and sensitive attributes. In this paper we are proposing a novel technique providing privacy on sensitive data is called Slicing, this technique divides the particular data into horizontally and vertically. Here we are showing that slicing is better data utility technique compare with generalization and this can provide membership disclosure protection. Alternative major advantage of slicing is it can handle highdimensional data. We exhibits how slicing provide membership disclosure protection and it develop an efficient algorithm for computing sliced data which are required l diversity. Our works confirm that slicing is better preserve data utility concept compare with generalization and more effective than bucketization, our workload involves the sensitive attributes. Our experiment also described that slicing is used to prevent membership disclosure protection.