Classification and Evaluation the Privacy Preserving Data Mining Techniques by using a Data Modification-based Framework

TL;DR

This paper introduces a data modification-based framework for classifying and evaluating privacy-preserving data mining techniques, facilitating better comparison and understanding of different approaches like perturbation and anonymization.

Contribution

It proposes a novel framework that categorizes privacy-preserving data mining techniques and uses functional criteria for their assessment, enhancing comparison and recognition of modern methods.

Findings

Framework effectively classifies techniques into perturbation and anonymization groups.

Allows detailed comparison based on eight functional criteria.

Helps identify overlaps and emerging approaches in privacy-preserving data mining.

Abstract

In recent years, the data mining techniques have met a serious challenge due to the increased concerning and worries of the privacy, that is, protecting the privacy of the critical and sensitive data. Different techniques and algorithms have been already presented for Privacy Preserving data mining, which could be classified in three common approaches: Data modification approach, Data sanitization approach and Secure Multi-party Computation approach. This paper presents a Data modification- based Framework for classification and evaluation of the privacy preserving data mining techniques. Based on our framework the techniques are divided into two major groups, namely perturbation approach and anonymization approach. Also in proposed framework, eight functional criteria will be used to analyze and analogically assessment of the techniques in these two major groups. The proposed framework provides a good basis for more accurate comparison of the given techniques to privacy preserving data mining. In addition, this framework allows recognizing the overlapping amount for different approaches and identifying modern approaches in this field.