A Review of Privacy Preserving Clustering in Data Mining Using Piecewise Vector Quantization

Privacy preservation has become a critical challenge in data mining applications due to the rapid growth of internet-based and cloud-based data sharing environments. While data mining techniques enable the extraction of valuable knowledge from large datasets, they also raise serious concerns regarding the confidentiality of sensitive information. Various privacy preserving data mining (PPDM) techniques such as cryptography, anonymization, perturbation, and secure multiparty computation have been proposed to address these issues. Among data mining methods, clustering techniques play a significant role in privacy preservation by grouping similar data while minimizing information disclosure. This review paper presents an analytical study of privacy preserving data mining techniques with a particular focus on privacy preserving clustering using Piecewise Vector Quantization (PVQ). The paper discusses existing PPDM approaches, highlights the role of clustering, explains the PVQ-based privacy preservation mechanism, identifies research gaps, and outlines future research directions.