A Fuzzy Approach to Preserve Data Privacy in Rule-Based Mining

In recent years a new class of data mining methods, called Privacy Preserving Data Mining (PPDM), has been developed. The aim of PPDM researches is to develop techniques; those could be applied to data bases without violating the privacy of individuals. In this study, a selective fuzzy membership function is used to perturb private data for preserving data privacy and a number of rule-based classifiers are used to evaluate our approach. In our purposed method beside preserving data privacy, effects of private data on data mining results are also preserved. Four datasets, taken from the UCI repository are employed for evaluation of our proposed approach. The aim of this study is to investigate the accuracy of different rule-based classification algorithms when data are perturbed by using selective Fuzzy Membership Functions.

Keywords:

privacy preserving , data mining , fuzzy , rule-based classifiers