Disclosing user relationships in email networks
Article
-
- Overview
-
- Research
-
- Identity
-
- Additional Document Info
-
- View All
-
Overview
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. © 2015, Springer Science%2bBusiness Media New York.
publication date
published in
Research
keywords
-
Anonymity; Mixes; Network communications; Statistical disclosure attack Computer programming; Mixing; Software engineering; Anonymity; E-mail networks; Network communications; Partial information; Patterns of communication; Positive predictive values; Statistical disclosure; Statistical information; Electronic mail
Identity
Digital Object Identifier (DOI)
Additional Document Info
start page
end page
volume
issue