Internal attacks in anonymous publish-subscribe P2P overlays

Privacy, in particular anonymity, is desirable in Online Social Networks (OSNs) like Twitter, especially when considering the threat of political repression and censorship. P2P-based publish-subscribe is a well suited paradigm for OSN scenarios as users can publish and follow topics of interest. However, anonymity in P2P-based publish-subscribe (pub-sub) has been hardly analyzed so far. Research on add-on anonymization systems such as Tor mostly focuses on large scale traffic analysis rather than malicious insiders. Therefore, we analyze colluding insider attackers in more detail that operate on the basis of timing information. For that, we model a generic anonymous pub-sub system, present an attacker model, and discuss timing attacks. We analyze these attacks by a realistic simulation model and discuss potential countermeasures. Our findings indicate that even few malicious insiders are capable to disclose a large number of participants, while an attacker using large amounts of colluding nodes achieves only minor additional improvements.