A taxonomy of privacy-preserving record linkage techniques

By Dinusha Vatsalan, Peter Christen, Vassilios S. Verykios. 2013

307 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Management Science and Operations Research

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Peter Christen
2. Dinusha Vatsalan
3. Vassilios S. Verykios
4. Giorgio Patrini
5. Richard Nock
6. Stephen Hardy
7. R. Schnell
8. Mazleena Salleh

In Information Systems

1. R. Schnell
2. Peter Christen
3. Dinusha Vatsalan
4. Vassilios S. Verykios
5. Mohammad Abdur Razzaque
6. Mazleena Salleh
7. Yousra Abdul Alsahib S. Aldeen
8. Harvey Goldstein

In Management Science and Operations Research

1. Peter Christen
2. Dinusha Vatsalan
3. R. Schnell
4. Vassilios S. Verykios
5. Giorgio Patrini
6. Richard Nock
7. Stephen Hardy
8. Mazleena Salleh

Citations in the corpus

• Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption (2017, background): “CLKs, resulting in a number of comparisons equal to the product of the datasets sizes. The most similar pairs are selected as matches, in a greedy fashion. Faster computation is possible by blocking [Vatsalan et al., 2013b]. The outputs of entity matching are two permutations ˙;˝and a mask m: ˙;˝des”
• Sensing as a service model for smart cities supported by Internet of Things (2013, unknown): “Techniques similar to privacy preserving data sharing ad matching [40] need to be developed in order to combine sensor data to anonymize entities / profiles (excluding sensitive data) later at the server level.”
• Efficient private record linkage of very large datasets (2013, result): “Since then, this approach has been used in different countries by different research teams and compares favourable to other approaches (Vatsalan et al. 2013).”
• Efficient two-party private blocking based on sorted nearest neighborhood clustering (2013, methodology): “Two different types of privacy techniques have been used to address the privacy aspect in PPRL [32].”
• Challenges in administrative data linkage for research (2017, background): “Achieving a balance between data protection and accuracy and usability of the resulting linked dataset is an ongoing area of research (Vatsalan et al., 2013).”
• A comprehensive review on privacy preserving data mining (2015, methodology): “Vatsalan et al. (2013) reviewed the technique called ‘Privacy-Preserving Record Linkage’ (PPRL), which allowed the linkage of databases to organizations by protecting the privacy.”