Extracting association patterns in network communications

In network communications, mixes provide protection against observers hiding the appearance of messages, patterns, length and links between senders and receivers. Statistical disclosure attacks aim to reveal the identity of senders and receivers in a communication network setting when it is protected by standard techniques based on mixes. This work aims to develop a global statistical disclosure attack to detect relationships between users. The only information used by the attacker is the number of messages sent and received by each user for each round, the batch of messages grouped by the anonymity system. A new modeling framework based on contingency tables is used. The assumptions are more flexible than those used in the literature, allowing to apply the method to multiple situations automatically, such as email data or social networks data. A classification scheme based on combinatoric solutions of the space of rounds retrieved is developed. Solutions about relationships between users are provided for all pairs of users simultaneously, since the dependence of the data retrieved needs to be addressed in a global sense. © 2015 by the authors; licensee MDPI, Basel, Switzerland.

Anonymity; Mixes; Network communications; Statistical disclosure attack Anonymity; Association patterns; Classification scheme; Contingency table; In networks; Model framework; Network communications; Statistical disclosure; Mixing; computer network; computer security; human; theoretical model; Computer Communication Networks; Computer Security; Humans; Models, Theoretical

VIVO