Catching Loosely Synchronized Behavior in Face of Camouflage
This addresses fraud detection for social networks and online applications, but it appears incremental as it focuses on a known issue without claiming a breakthrough.
The paper tackles the problem of detecting fraud in online platforms where fake accounts manipulate ranking systems through coordinated interactions, but the abstract does not provide specific results or numbers.
Fraud has severely detrimental impacts on the business of social networks and other online applications. A user can become a fake celebrity by purchasing "zombie followers" on Twitter. A merchant can boost his reputation through fake reviews on Amazon. This phenomenon also conspicuously exists on Facebook, Yelp and TripAdvisor, etc. In all the cases, fraudsters try to manipulate the platform's ranking mechanism by faking interactions between the fake accounts they control and the target customers.