eCite Digital Repository

Disclosing user relationships in email networks

Citation

Portela, J and GarcA a Villalba, LJ and Silva Trujillo, AG and Sandoval Orozco, AL and Kim, TH, Disclosing user relationships in email networks, Journal of Supercomputing, 72, (10) pp. 3787-3800. ISSN 0920-8542 (2015) [Refereed Article]

Copyright Statement

Copyright 2015 Springer Science+Business Media New York

DOI: doi:10.1007/s11227-015-1524-7

Abstract

To reveal patterns of communications of users in a network, an attacker may repeatedly obtain partial information on behavior and finally derive relationships between pairs of users through the modeling of this statistical information. This work is an enhancement of a previously presented statistical disclosure attack. The improvement of the attack is based on the use of the EM algorithm to improve the estimation of messages sent by users and to derive what pairs of users really communicate. Two methods are presented using the EM algorithm and the best method is used over real email data over 32 different network domains. Results are encouraging with high classification and positive predictive value rates.

Item Details

Item Type:Refereed Article
Keywords:anonymity, mixes, network communications, statistical disclosure attack
Research Division:Technology
Research Group:Communications Technologies
Research Field:Computer Communications Networks
Objective Division:Information and Communication Services
Objective Group:Communication Networks and Services
Objective Field:Communication Networks and Services not elsewhere classified
Author:Kim, TH (Dr Tai Kim)
ID Code:110670
Year Published:2015
Web of Science® Times Cited:1
Deposited By:Computing and Information Systems
Deposited On:2016-08-09
Last Modified:2017-11-03
Downloads:0

Repository Staff Only: item control page