Shedding Light on the Dark Web: Authorship Attribution in Radical Forums

Abstract

Online users tend to hide their real identities by adopting different names on the Internet. On Facebook or LinkedIn, for example, people usually appear with their real names. On other standard websites, such as forums, people often use nicknames to protect their real identities. Aliases are used when users are trying to protect their anonymity. This can be a challenge to law enforcement trying to identify users who often change nicknames. In unmonitored contexts, such as the dark web, users expect strong identity protection. Thus, without censorship, these users may create parallel social networks where they can engage in potentially malicious activities that could pose security threats. In this paper, we propose a solution to the need to recognize people who anonymize themselves behind nicknames—the authorship attribution (AA) task—in the challenging context of the dark web: specifically, an English-language Islamic forum dedicated to discussions of issues related to the Islamic world and Islam, in which members of radical Islamic groups are present. We provide extensive analysis by testing models based on transformers, styles, and syntactic features. Downstream of the experiments, we show how models that analyze syntax and style perform better than pre-trained universal language models.

PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models

“…Pre-training seems to be a winning strategy to boost generalization. In fact, pre-trained models generalize better on outof-distribution data and can detect such data better than non-pre-trained methods (Hendrycks et al, 2020;Ranaldi et al, 2022b). However, these models need a significant number of training instances to exploit this generalization ability in downstream tasks (Tänzer et al, 2022).…”