STor: Social Network based Anonymous Communication in Tor

Abstract: Anonymity networks hide user identities with the help of relayed anonymity routers. However, the state-of-the-art anonymity networks do not provide an effective trust model. As a result, users cannot circumvent malicious or vulnerable routers, thus making them susceptible to malicious router based attacks (e.g., correlation attacks). In this paper, we propose a novel social network based trust model to help anonymity networks circumvent malicious routers and obtain secure anonymity. In particular, we design an input independent fuzzy model to determine trust relationships between friends based on qualitative and quantitative social attributes, both of which can be readily obtained from existing social networks. Moreover, we design an algorithm for propagating trust over an anonymity network. We integrate these two elements in STor, a novel social network based Tor. We have implemented STor by modifying the Tor's source code and conducted experiments on PlanetLab to evaluate the effectiveness of STor. Both simulation and PlanetLab experiment results have demonstrated that STor can achieve secure anonymity by establishing trust-based circuits in a distributed way. Although the design of STor is based on Tor network, the social network based trust model can be adopted by other anonymity networks.