A Supermodularity-Based Differential Privacy Preserving Algorithm for Data Anonymization

Project Discription

In this chapter proposed method is explained step by step where different parameters are covered for hiding the direct discriminating items. Whole work is broadly divided into few blocks such as pre-processing, frequent rule generation from the dataset which help in identifying the information, next is to filter those rules from the frequent set that discriminate attribute values from others. Finally all filtered rules are perturbed one by one so that all the sensitive attribute values will not lead to any strong decision which is unfavourable.

Mining of individual information from the raw dataset leads to retrieve information. Some unfair rules or information generate from these raw data would directly harm individual, community, class, etc privacy. So protection of this information from the mining algorithm is required. Privacy preserving mining is applied to provide protection of that information in the dataset.  But privacy technique should be so perfect that it maintain dataset utility as well after applying privacy technique. All fair information or rules present in the dataset remain unaffected, while unfair information should be suppressed below a threshold value.

Project Sample Image