Quality Evaluation of an Anonymized Dataset

Samuel Fletcher, Md Zahidul Islam

Research output: Book chapter/Published conference paperConference paper

7 Citations (Scopus)
4 Downloads (Pure)

Abstract

In this study we argue that the traditional approachof evaluating information quality in an anonymized (or otherwisemodified) dataset is questionable. We propose a novel and simpleapproach to evaluate the information quality of a dataset, andthereby the quality of anonymization techniques. We carry outexperiments on eleven datasets and the empirical results stronglysupport our arguments. We also present some extensions of ourapproach that provide additional insight into the informationquality of modified data.
Original languageEnglish
Title of host publicationICPR 2014
EditorsMagnus Borga
Place of PublicationUnited States
PublisherIEEE
Pages3594-3599
Number of pages6
ISBN (Electronic)9781479952090
DOIs
Publication statusPublished - 2014
EventICPR 2014: International Conference on Pattern Recognition - Stockholm Waterfront, Stockholm, Sweden
Duration: 24 Aug 201428 Aug 2014
http://www.iapr.org/archives/icpr2014/

Conference

ConferenceICPR 2014
CountrySweden
CityStockholm
Period24/08/1428/08/14
OtherWelcome to the 22nd International Conference on Pattern Recognition in Stockholm, August 2014, hosted by the Swedish Society for Automated Image Analysis (SSBA). ICPR 2014 will be an international forum for discussions on recent advances in the fields of Pattern Recognition; Machine Learning and Computer Vision; and on applications of these technologies in various fields.
Internet address

Cite this

Fletcher, S., & Islam, M. Z. (2014). Quality Evaluation of an Anonymized Dataset. In M. Borga (Ed.), ICPR 2014 (pp. 3594-3599). IEEE. https://doi.org/10.1109/ICPR.2014.618