eCite Digital Repository

Disclosing user relationships in email networks


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


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:Engineering
Research Group:Communications engineering
Research Field:Network engineering
Objective Division:Information and Communication Services
Objective Group:Communication technologies, systems and services
Objective Field:Communication technologies, systems and services not elsewhere classified
UTAS Author:Kim, TH (Dr Tai Kim)
ID Code:110670
Year Published:2015
Web of Science® Times Cited:2
Deposited By:Information and Communication Technology
Deposited On:2016-08-09
Last Modified:2018-03-16

Repository Staff Only: item control page