Quantifying fine-grained privacy risk and representativeness in medical data

Authors:
Xiaoqian Jiang;Samuel Cheng;Lucila Ohno-Machado
Affiliations:
University of California at San Diego, La Jolla, CA, USA;University of Oklahoma, Tulsa, OK, USA;University of California at San Diego, La Jolla, CA, USA
Venue:
Proceedings of the 2011 workshop on Data mining for medicine and healthcare
Year:
2011

Citing 9
Cited 0

Multidimensional binary search trees used for associative searching

Communications of the ACM
k-anonymity: a model for protecting privacy

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
Latent dirichlet allocation

The Journal of Machine Learning Research
Incognito: efficient full-domain K-anonymity

Proceedings of the 2005 ACM SIGMOD international conference on Management of data
On k-anonymity and the curse of dimensionality

VLDB '05 Proceedings of the 31st international conference on Very large data bases
Disclosure risk measures for microdata

SSDBM '03 Proceedings of the 15th International Conference on Scientific and Statistical Database Management
L-diversity: Privacy beyond k-anonymity

ACM Transactions on Knowledge Discovery from Data (TKDD)
Privacy-preserving data publishing: A survey of recent developments

ACM Computing Surveys (CSUR)
An ad omnia approach to defining and achieving private data analysis

PinKDD'07 Proceedings of the 1st ACM SIGKDD international conference on Privacy, security, and trust in KDD

Quantified Score

Hi-index	0.00

Visualization

Abstract

The current way that privacy is protected suggests lack of consideration of privacy needs of different types of medical records. Without knowing how representative and sensitive individual records are, methods built on the top of unwarranted assumptions could be misleading and even erroneous, e.g. over-protecting of a subset of the records while under-protecting of the rest. This article developed a novel framework to quantify the fine-grained privacy risk and representativeness of individual records in a medical database. Our implementation leveraged the KD-tree, an efficient data structure, to do range queries. We used real-data to demonstrate the feasibility of the proposed method.