Backpage and Bitcoin: Uncovering Human Traffickers

TitleBackpage and Bitcoin: Uncovering Human Traffickers
Publication TypeConference Paper
Year of Publication2017
AuthorsPortnoff, R. S., Huang D. Yuxing, Doerfler P., Afroz S., & McCoy D.
Published inProceedings of KDD 2017

Sites for online classied ads selling sex are widely used by human trackers to support their pernicious business. The sheer quantity of ads makes manual exploration and analysis unscalable. In addition, discerning whether an ad is advertising a tracked victim or an independent sex worker is a very dicult task. Very little concrete ground truth (i.e., ads denitively known to be posted by a tracker) exists in this space. In this work, we develop tools and techniques that can be used separately and in conjunction to group sex ads by their true owner (and not the claimed author in the ad). Specically, we develop a machine learning classier that uses stylometry to distinguish between ads posted by the same vs. dierent authors with 90% TPR and 1% FPR. We also design a linking technique that takes advantage of leakages from the Bitcoin mempool, blockchain and sex ad site, to link a subset of sex ads to Bitcoin public wallets and transactions. Finally, we demonstrate via a 4-week proof of concept using Backpage as the sex ad site, how an analyst can use these automated approaches to potentially nd human trackers. 


This work was supported in part by the National Science Foundation under grant CNS-1619620, by the Amazon “AWS Cloud Credits for Research”, by the U.S. Department of Education, by Giant Oak, and by gifts from Google and Thorn. We thank all the people that provided us with assistance in analysis; in particular we thank Chainalysis for the use of their tools and their contribution to this work. Any opinions, ndings, and conclusions or recommendations expressed in this material are those of the authors and do not necessarily reect the views of the sponsors. 

ICSI Research Group

Networking and Security