@inproceedings{049407f8351842c99ad223f5609d4d9b,
title = "Sorted nearest neighborhood clustering for efficient private blocking",
abstract = "Record linkage is an emerging research area which is required by various real-world applications to identify which records in different data sources refer to the same real-world entities. Often privacy concerns and restrictions prevent the use of traditional record linkage applications across different organizations. Linking records in situations where no private or confidential information can be revealed is known as privacy-preserving record linkage (PPRL). As with traditional record linkage applications, scalability is a main challenge in PPRL. This challenge is generally addressed by employing a blocking technique that aims to reduce the number of candidate record pairs by removing record pairs that likely refer to non-matches without comparing them in detail. This paper presents an efficient private blocking technique based on a sorted neighborhood approach that combines k-anonymous clustering and the use of public reference values. An empirical study conducted on real-world databases shows that this approach is scalable to large databases, and that it can provide effective blocking while preserving k-anonymous characteristics. The proposed approach can be up-to two orders of magnitude faster than two state-of-the-art private blocking techniques, k-nearest neighbor clustering and Hamming based locality sensitive hashing.",
keywords = "K-anonymity, Locality sensitive hashing, Nearest neighbor clustering, Reference values, Scalability, Sorted neighborhood",
author = "Dinusha Vatsalan and Peter Christen",
year = "2013",
doi = "10.1007/978-3-642-37456-2_29",
language = "English",
isbn = "9783642374555",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
number = "PART 2",
pages = "341--352",
booktitle = "Advances in Knowledge Discovery and Data Mining - 17th Pacific-Asia Conference, PAKDD 2013, Proceedings",
edition = "PART 2",
note = "17th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2013 ; Conference date: 14-04-2013 Through 17-04-2013",
}