Tor is a popular ‘darknet’, a network that aims to conceal its users’ identities and online activities. Darknets are composed of host machines that cannot be accessed by conventional means, which is why the content they host is typically not indexed by traditional search engines like Google and Bing. On Tor, web content and other types of services can anonymously be made available as so-called hidden services. Obviously, where anonymity can be a vehicle for whistleblowers and political
dissidents to exchange information, the reverse of the medal is that it also attracts malicious actors. In our research, we aim to develop a detailed understanding of what Tor is being used for. We applied classification and topic model-based text mining techniques to the content of over a thousand Tor hidden services in order to model their thematic organization and linguistic diversity. As far as we are aware, this paper presents the most comprehensive content-based analysis of Tor to date.
[Spitters2014] Martijn Spitters, Stefan Verbruggen, and Mark van Staalduinen. Towards a comprehensive insight into the thematic organization of the tor hidden services. In Joint Intelligence and Security Informatics Conference (JISIC), pages 220-223, The Hague, The Netherlands, Sep 2014. IEEE.