Privacy-Preserving Record Linkage

Abstract

Abstract. Record linkage has a long tradition in both the statistical and the computer science literature. We survey current approaches to the record linkage problem in a privacy-aware setting and contrast these with the more traditional literature. We also identify several important open questions that pertain to private record linkage from different perspectives.

Privacy‐preserving record linkage

“…A number of reviews, tutorials and taxonomies on available techniques have been published since 2010, for example Hall & Fienberg (2010); Navarro-Arribas & Torra (2012); ; Vatsalan et al (2013) and . Therefore, only the basic approaches will be described shortly.…”

Valid Statistical Inference on Automatically Matched Files

“…An overview of techniques are given by [4]. Although we focus on the statistical methodology in this paper, in principle the ideas could be applied in a privacy-preserving way (e.g., by instantiating our method inside a cryptographic framework).…”

Privacy Preserving Group Linkage

“…The PPGL problem could be solved by existing privacy-preserving set intersection protocols [1,4,11]. However, in the case where Bob holds a large number of groups with overlapping records, and Alice needs to check each of her groups against all Bob's groups, the existing solutions suffer from group membership inference problem, as shown in the following example.…”

“…Privacy-preserving record linkage with exact matching is very similar to privacy-preserving set intersection: to identify the intersection of two sets of records without revealing private records. Surveys could be found at [26,11]. Among the more popular approaches, solutions based on homomorphic encryption (e.g.…”