Towards Robust, Explainable, and Privacy-Friendly Sybil Detection

Online Social Networks (OSN) are well established tools for cooperation and exchange of ideas between peers. The authenticity of peers cannot be verified easily but is derived from trust relations inside the OSN. With the help of sybil attacks, this can be exploited by malicious actors to spread misinformation, for example. Several countermeasures against sybil attacks have been proposed in the literature. However, sybil defence methods are very rarely implemented in real-world OSNs, the use of global graph structures leads to explainability problems of misclassifications and the use of personal metadata is not privacy-friendly. Moreover, all structure-based defence mechanisms depent on a fundamental theoretical assumption, that does not hold in real-world scenarios.