Playing with Sybil

Recommender systems have become quite popular recently. However, such systems are vulnerable to several types of attacks that target user ratings. One such attack is the Sybil attack where an entity masquerades as several identities with the intention of diverting user ratings. In this work, we propose classical and spatial evolutionary game theory as possible solutions to the Sybil attack in recommender systems. We model the attack using the two techniques and use replicator dynamics in the classical model to solve for evolutionary stable strategies. Results from both models agree that under conditions that are easily achievable by a system administrator, the probability of an attack strategy drops to zero implying degraded fitness for Sybils that eventually die out.