@inproceedings{1ce8dd1c6dda49c8a199426f8cacb661,
title = "Data Anonymization as a Vector Quantization Problem: Control Over Privacy for Health Data",
abstract = "This paper tackles the topic of data anonymization from a vector quantization point of view. The admitted goal in this work is to provide means of performing data anonymization to avoid single individual or group re-identification from a data set, while maintaining as much as possible (and in a very specific sense) data integrity and structure. The structure of the data is first captured by clustering (with a vector quantization approach), and we propose to use the properties of this vector quantization to anonymize the data. Under some assumptions over possible computations to be performed on the data, we give a framework for identifying and “pushing back outliers in the crowd”, in this clustering sense, as well as anonymizing cluster members while preserving cluster-level statistics and structure as defined by the assumptions (density, pairwise distances, cluster shape and members...).",
keywords = "512 Business and Management, Distance Function, Vector Quantization, Pairwise Distance, Differential Privacy, Cluster Element",
author = "Yoan Miche and Ian Oliver and Silke Holtmanns and Aapo Kalliola and Anton Akusok and Amaury Lendasse and Kaj-Mikael Bj{\"o}rk",
year = "2016",
month = aug,
day = "23",
doi = "10.1007/978-3-319-45507-5_13",
language = "English",
isbn = "978-3-319-45506-8",
series = " Lecture Notes in Computer Science book series (LNCS)",
publisher = "Springer",
pages = "193--203 ",
booktitle = "CD-ARES 2016: Availability, Reliability, and Security in Information Systems",
address = "International",
}