Hypergraph model for anonymous communications

Distributed networks such as virtual networks like P2P networks or physical networks like mobile ad hoc networks have no centralized structure. Communications across these networks are exposed to attacks, particularly against the respect for private information of users. Two ideas are used to improve the security of users´ privacy. The first is gathering of users in communities of trust. The second is the use of anonymity techniques that preserve identity of users but also of these communities of trust. In this paper, we propose HypAnoCom, a new model for anonymous communications based on hypergraph paradigm. Participants belong to different communities can communicate without disclosing their identities. We develop an algorithm for discovering minimal transversals. Those transversals are used to preserve privacy of users or groups. Indeed, we define a routing protocol based on selective hierarchy to insure communications. We show that our model satisfies following security conditions: identity privacy, location privacy and robustness against several attacks. Our model is particularly suitable for distributed and dynamic networks such as Ad-hoc mobile and Peer-to-Peer networks. Our model tackles churn by using hyperedges at each hop.