Strangers intrusion detection-detecting spammers and fake profiles in social networks based on topology anomalies

Michael Fire, Gilad Katz, Yuval Elovici

Human journal 1 (1), 26-39, 2012

Today’s social networks are plagued by numerous types of malicious profiles which can range from socialbots to sexual predators. We present a novel method for the detection of these malicious profiles by using the social network’s own topological features only. Reliance on these features alone ensures that the proposed method is generic enough to be applied on a range of social networks. The algorithm has been evaluated on several social networks and was found to be effective in detecting various types of malicious profiles. We believe this method is a valuable step in the increasing battle against social network spammers, socialbots, and sexual predictors.