Privacy preserving record linkage approaches

Abstract

Privacy-preserving record linkage is a very important task, mostly because of the very sensitive nature of the personal data. The main focus in this task is to find a way to match records from among different organisation data sets or databases without revealing competitive or personal information to non-owners. Towards accomplishing this task, several methods and protocols have been proposed. In this work, we propose a certain methodology for preserving the privacy of various record linkage approaches and we implement, examine and compare four pairs of privacy preserving record linkage methods and protocols. Two of these protocols use n-gram based similarity comparison techniques, the third protocol uses the well known edit distance and the fourth one implements the Jaro-Winkler distance metric. All of the protocols used are enhanced by private key cryptography and hash encoding. This paper presents also a blocking scheme as an extension to the privacy preserving record linkage methodology. Our comparison is backed up by extended experimental evaluation that demonstrates the performance achieved by each of the proposed protocols. Privacy preserving record linkage approaches 207His main research interests include privacy and security in advanced database systems, data mining, and data reconciliation. He has published over 60 papers in major refereed journals and international conferences and workshops and he has served in the program committees of several international scientific events.

Efficient privacy-aware record integration

“…At the same time, privacy concerns for sharing personal records has led to the development of private record linkage (PRL) protocols [3, 4, 16, 17, 23, 24, 28, 30]. PRL protocols tend to use two primary mechanisms to integrate data while protecting the privacy of the sensitive information: secure multiparty computation (SMC) and data transformation.…”

“…To achieve their goal, PRL protocols must be resistant to typographical errors (e.g., “john” vs. “jonh”) that can arise in real world data sources [14, 15]. Previous PRL algorithms [1, 16, 17, 25, 28] achieve this feat by computing the similarity of record pairs via two fundamental mechanisms: 1) secure multi-party computation (SMC) [2, 10] and 2) similarity preserving data transformation [24, 25, 30]. …”

Geospatial cryptography: enabling researchers to access private, spatially referenced, human subjects data for cancer control and prevention

“…This problem spans the research continuum, from basic discovery to translational research (VanWey et al 2005). Both epidemiological and laboratory studies may employ data linkage using individual identifiers such as name and address (Rushton et al 2006; Verykios et al 2009) to link health data with Medicare and other government databases (National Research Council 2007). Common linking techniques require identifying information to facilitate high match rates, but this is often not permissible for privacy reasons.…”

Quantifying the correctness, computational complexity, and security of privacy-preserving string comparators for record linkage

“…We recognize that several reviews of PPSCs have been conducted [25, 26, 27, 28], but they lack either the breadth ( i.e. , range of methods considered) or the depth necessary ( i.e.…”

“…Another paper [27] provides an overview of privacy-preserving record linkage, current approaches, and open research questions, but again does not provide a formal, quantified analysis of existing approaches. In another study, Verykios and colleagues [28] performed a principled review of PPSCs, but focused on string comparison, rather than string comparison within the context of record linkage. Moreover, the latter study also neglected a formal security analysis of the PPSCs.…”