If you want to get to the bottom of a crime , it ’s often said that you should just “ follow the money ” . In the world of cryptocurrencies and faceless online pseudonym , that ’s a footling bit ruffianly .
Computer scientist have now developed the first automate system of rules to track down exploitative sex trafficking rings working on the net . The creature finds connections between online publicizing posts and data from the digital currency Bitcoin using a series of machine encyclopaedism algorithms .
The researchwas recently presented at theSIGKDD Conference on Knowledge Discovery and Data Miningin Nova Scotia , Canada .
The AI tool starts by canvass the linguistic communication , elan , and structure of the post on online program such as Backpage and Craigslist . It can determine which adverts show victims who are push into prostitution , as opposed to those who are uncoerced participants . It ’s also able-bodied to tell apart whether numerous adverts for unlike sexual urge worker share a individual writer , a distinctive sign there is a pandar or trafficking closed chain involved .
“ Is the pimp behind that mail service for Backpage also behind this Wiley Post in Craigslist ? Is he the same man who observe receiving Bitcoin for traffic girls?“Rebecca Portnoff , a UC Berkeley Ph.D. candidate in computer science , who recrudesce the tool as part of her dissertation , allege in astatement . " Questions like these are answerable only through more advanced technical tools – exactly what we ’ve built in this work – that link ads together using payment mechanisms and the language in the advert themselves . ”
Once an author is flagged as in question , another AI algorithm looks at the Bitcoin blockchain . The blockchain is a digital ledger where all dealing and accounts are publicly logged , however the existent - life-time identities of the payees remain anonymous . The second algorithmic program looks at how much money is being exchanged and when the dealing take place , then identify whether there are any links between this data and the information in the fishy advert post . pair together , this can be used to find the indistinguishability of a criminal or a traffic ring .
The rest of the study ( ie verifying this author is indeed taking part in illegal activity ) has to be carried out by the police . However , the tool has already shown it hold the potential to be a key shaft for jurisprudence enforcement and nonprofit organizations trying to distinguish victims of human trafficking . The investigator have tested out their AI tool using a sampling of 10,000 real grownup ads on Backpage . It was able to correctly distinguish a wary source with up to 89 per centum accuracy .
“ sex activity trafficking of children hides in apparent vision within the huge on-line escort environment . It ’s difficult for investigators to sieve through the heap of data and figure out what is important and what is not when look for a child , ” say Julie Cordua , chief executive officer of Thorn , an international anti - human trafficking NGO . “ This type of research is critical to advancing this workplace and aid tec find children quicker and reduce the meter in psychic trauma .
