Automatic User Profiling in Darknet Markets: a Scalability Study

TL;DR

This paper evaluates the scalability and reliability of user profiling techniques in dark web markets, comparing their effectiveness across different online communities with varying user demographics and anonymity levels.

Contribution

It provides a comprehensive analysis of stylometry-based profiling methods' performance on new, realistic datasets resembling dark web user populations.

Findings

Profiling techniques show varying reliability across different online domains.

Demographic differences impact the effectiveness of user profiling.

The study highlights limitations of current methods in underground forum contexts.

Abstract

In this study, we investigate the scalability of state-of-the-art user profiling technologies across different online domains. More specifically, this work aims to understand the reliability and limitations of current computational stylometry approaches when these are applied to underground fora in which user populations potentially differ from other online platforms (predominantly male, younger age and greater computer use) and cyber offenders who attempt to hide their identity. Because no ground truth is available and no validated criminal data from historic investigations is available for validation purposes, we have collected new data from clearweb forums that do include user demographics and could be more closely related to underground fora in terms of user population (e.g., tech communities) than commonly used social media benchmark datasets showing a more balanced user population.