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

Abstract

Record linkage is the task of identifying records from disparate data sources that refer to the same entity. It is an integral component of data processing in distributed settings, where the integration of information from multiple sources can prevent duplication and enrich overall data quality, thus enabling more detailed and correct analysis. Privacy-preserving record linkage (PPRL) is a variant of the task in which data owners wish to perform linkage without revealing identifiers associated with the records. This task is desirable in various domains, including healthcare, where it may not be possible to reveal patient identity due to confidentiality requirements, and in business, where it could be disadvantageous to divulge customers' identities. To perform PPRL, it is necessary to apply string comparators that function in the privacy-preserving space. A number of privacy-preserving string comparators (PPSCs) have been proposed, but little research has compared them in the context of a real record linkage application. This paper performs a principled and comprehensive evaluation of six PPSCs in terms of three key properties: 1) correctness of record linkage predictions, 2) computational complexity, and 3) security. We utilize a real publicly-available dataset, derived from the North Carolina voter registration database, to evaluate the tradeoffs between the aforementioned properties. Among our results, we find that PPSCs that partition, encode, and compare strings yield highly accurate record linkage results. However, as a tradeoff, we observe that such PPSCs are less secure than those that map and compare strings in a reduced dimensional space.

Evaluation of record linkage of mortality data between a health and demographic surveillance system and national civil registration system in South Africa

“…Records matched by one rule were removed from the pool of records to be matched with subsequent rules in both datasets. The Jaro-Winkler string comparator (JW) [30], which is particularly well-suited for personal names [31], returning values between 0 (complete disagreement) and 1 (exact agreement) as a measure of similarity between two strings [30,32], was used to accommodate typographical errors on surnames. We set a cut-off for designating pairs of surnames as matches to a JW score ≥ 0.85, which is higher than in previous studies [30,33].…”

Efficient Similarity Search over Encrypted Data

“…Unfortunately, such secure multi-party computation based techniques incur substantial computational resources. According to a recent survey [11], secure edit distance computations [10] require over two years to compute similarity between two datasets of 1000 strings each, on a commodity server. It is apparent that we need efficient methods to perform similarity search over large amount of encrypted data.…”

Ontology Based Framework to Configure the Organizational Goal Analysis and Decision-Making

“…Record linkage is highly used to identify data that being linked, so all datasets under consideration should ideally undergo a matching process prior to the record linkage [13]. Even though there are studies have been carried out in various issues such as software [14,15], data privacy [16,17] and security [13], we suggest it is important to develop a standard set of approach to show the relationship between data, attributes and organizational goals. Even though the term is defined as record linkage but we use the term data linkage as an effort to identify the relationship between data, attributes and organizational goals because we attempt to identify the linkage for each data and attributes that relates to the organizational goals.…”