IMR based Anonymization for Privacy Preservation in Data Mining

Abstract

Privacy Preserving Data Mining (PPDM) is a data mining research area that aims to protect individual's personal information from unsolicited or unauthorized disclosure. Privacy relates to personal information that a person would not wish others to know without authorization, and to a person's right to be free from the attention of others (UN Declaration of Human Rights, 1948). Advances in computer technology, social networking sites, communications and improvement in hardware technologies have made it possible to collect and store huge amounts of data in digital form. This results in the increasing ability to collect large amounts of personal information. However the collection and sharing of data have also raised a number of ethical issues. Such issues include privacy, data security, and intellectual property rights. These Privacy Issues violates a person's right and brings dignitary harm to the research participant. In addition, it would also bring social mortification, shame, disgrace, and damage to social and economic status. In recent years, numerous data mining algorithms combining privacy preserving techniques have been developed that hide sensitive item sets or patterns. An important issue here is to decide which privacy preserving technique gives better protection for sensitive information. It is also important to access the quality of the result as well as the performance of the algorithm, after applying the privacy preserving techniques. In this paper, we propose IMR (I - Buckets based Map Reducing) based Anonymization and present a brief introduction of different kinds of PPDM techniques with their merits and demerits. Our work highlights some considerations about future work and promising directions in the perspective of privacy preservation in data mining.