Disclosing user relationships in email networks

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 statistica...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2016-10, Vol.72 (10), p.3787-3800
Main Authors: Portela, Javier, García Villalba, Luis Javier, Silva Trujillo, Alejandra Guadalupe, Sandoval Orozco, Ana Lucila, Kim, Tai-Hoon
Format: Article
Language:English
Subjects:
Compilers
Computer Science
Interpreters
Messages
Processor Architectures
Programming Languages
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-015-1524-7