An evolutionary feature set decomposition based anonymization for classification workloads: Privacy Preserving Data Mining

Abstract

Privacy has become an important concern while publishing micro data about a population. The emerging area called privacy preserving data mining (PPDM) focus on individual privacy without compromising data mining results. An adversarial exploitation of published data poses a risk of information disclosure about individuals. On the other hand, imposing privacy constraints on the data results in substantial information loss and compromises the legitimate data analysis. Motivated by the increasing growth of PPDM algorithms, we first investigate the privacy implications and the crosscutting issues between privacy versus utility of data. We present a privacy model that embeds the anonymization procedure in to a learning algorithm and this has mitigated the additional overheads imposed on data mining tasks. Our primary concern about PPDM is that the utility of data should not be compromised by the transformation applied. Different data mining classification workloads are analyzed with the proposed anonymization procedure for any side effects incurred. It is shown empirically that classification accuracy obtained for most of the datasets outperforms the results obtained with original dataset.