Towards Detecting Anomalous User Behavior in Online Social Networks
Users increasingly rely on crowd-sourced information, such as reviews on Yelp and Amazon, and liked posts and ads on Facebook. This has led to a market for blackhat promotion techniques via fake (e.g., Sybil) and compromised accounts, and collusion networks. Existing approaches to detect such behavior relies mostly on supervised (or semi-supervised) learning over known (or hypothesized) attacks. They are unable to detect attacks missed by the operator while labeling, or when the attacker changes strategy.