Full Citation

Title: m-Color: Perservering Proximity Privacy for Categorical Sensitive Data

Citation Type: Journal Article

Publication Year: 2013

ISBN:

ISSN:

DOI:

NSFID:

PMCID:

PMID:

Abstract: A lately privacy preservation for numerical data has attracted great attention. The concept of (,m)-anonymity was proposed and solved the problem of data privacy preservation for numerical sensitiveattributes, but it made no progress for categorical sensitive attributes. In this paper, we address theproblem of proximity privacy in publishing categorical sensitive data. When applying the traditionalapproach to anonymize the data and generalize the QI-groups, some sensitive attribute values withsemantical proximity may exist in the same QI-group, and thus lead to privacy leakage. To remedy thisissue, the concept of m-Color constraint is introduced and a method based on the m-Color constraintis proposed to prevent such kind of privacy leakage. To improve the data utility of anonymized table,the properties of m-Color constraint and related generalization algorithm are also given. Extensiveexperiments on real data are provided to explain practicality and efficiency of the algorithm proposedin this paper.

User Submitted?: No

Authors: Wang, Wei; He, Xianmang; Chen, Huahui; Wang, Qidong; Li, Yujia

Periodical (Full): Journal of Computational Information Systems

Issue: 9

Volume: 17

Pages: 6831-6841

Data Collections: IPUMS USA

Topics: Methodology and Data Collection

Countries: