A Non-Parametric Learning Approach to Identify Online Human Trafficking

Human trafficking has received increased national and societal concern over the past decade [1]. According to the United Nation [2], human trafficking is defined as the modern slavery or the trade of humans mostly for the purpose of sexual exploiting and forced labor, via different improper ways including force, fraud and deception. Human trafficking is among the challenging problems facing the law enforcement-it is difficult to identify victims and counter traffickers. Before the advent of the Internet, pimps were under the risks of being arrested by law enforcement, while advertising their victims on the streets [3]. However, the move to the Internet, has made it easier and less dangerous for both sex buyers and sellers, especially for the pimps [4] as they no longer needed to advertise on the streets. There are now plethora of websites that host and provide sexual services, under categories of escort, adult entertainment, massage services, etc., which help pimps, traffickers and sex buyers (a.k.a.