Privacy-preserving record linkage using local sensitive hash and private set intersection

TL;DR

This paper introduces a new privacy-preserving record linkage protocol combining private set intersection and local sensitive hashing, enabling efficient and practical linking of large datasets while maintaining privacy.

Contribution

The paper proposes a novel PPRL protocol that integrates PSI and LSH, achieving linear runtime and practical performance for large datasets.

Findings

Runs in linear time for large datasets

Links datasets with up to 2^20 records in under an hour

Provides formal privacy guarantees

Abstract

The amount of data stored in data repositories increases every year. This makes it challenging to link records between different datasets across companies and even internally, while adhering to privacy regulations. Address or name changes, and even different spelling used for entity data, can prevent companies from using private deduplication or record-linking solutions such as private set intersection (PSI). To this end, we propose a new and efficient privacy-preserving record linkage (PPRL) protocol that combines PSI and local sensitive hash (LSH) functions, and runs in linear time. We explain the privacy guarantees that our protocol provides and demonstrate its practicality by executing the protocol over two datasets with $2^{20}$ records each, in $11-45$ minutes, depending on network settings.