Breadcrumb

 
 

Anonymity meets game theory: secure data integration with malicious participants

Title:

Anonymity meets game theory: secure data integration with malicious participants

Mohammed, Noman and Fung, Benjamin C.M. and Debbabi, Mourad (2011) Anonymity meets game theory: secure data integration with malicious participants. The VLDB Journal, 20 (4). pp. 567-588. ISSN 1066-8888

[img]
Preview
PDF
449Kb

Official URL: http://dx.doi.org/10.1007/s00778-010-0214-6

Abstract

Data integration methods enable different data providers to flexibly integrate their expertise and deliver highly customizable services to their customers. Nonetheless, combining data from different sources could potentially reveal person-specific sensitive information. In VLDBJ 2006, Jiang and Clifton (Very Large Data Bases J (VLDBJ) 15(4):316–333, 2006) propose a secure Distributed k-Anonymity (DkA) framework for integrating two private data tables to a k-anonymous table in which each private table is a vertical partition on the same set of records. Their proposed DkA framework is not scalable to large data sets. Moreover, DkA is limited to a two-party scenario and the parties are assumed to be semi-honest. In this paper, we propose two algorithms to securely integrate private data from multiple parties (data providers). Our first algorithm achieves the k-anonymity privacy model in a semi-honest adversary model. Our second algorithm employs a game-theoretic approach to thwart malicious participants and to ensure fair and honest participation of multiple data providers in the data integration process. Moreover, we study and resolve a real-life privacy problem in data sharing for the financial industry in Sweden. Experiments on the real-life data demonstrate that our proposed algorithms can effectively retain the essential information in anonymous data for data analysis and are scalable for anonymizing large data sets.

Divisions:Concordia University > Faculty of Engineering and Computer Science > Concordia Institute for Information Systems Engineering
Item Type:Article
Refereed:Yes
Authors:Mohammed, Noman and Fung, Benjamin C.M. and Debbabi, Mourad
Journal or Publication:The VLDB Journal
Date:2011
Keywords:k-anonymity, Secure data integration, Privacy, Classification
ID Code:36256
Deposited By:DAVID MACAULAY
Deposited On:22 Dec 2011 16:00
Last Modified:31 Oct 2012 10:31
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Document Downloads

More statistics for this item...

Concordia University - Footer