Wednesday, October 18, 2017
Home / Security / Researchers can identify underground users via Linguistics

Researchers can identify underground users via Linguistics

Around 80 percent who wrote at least 5000 words across their posts could identify certain anonymous underground forum users, researchers state.

Function words are very specific to the writer. Even if you are writing a thesis, you’ll probably use the same function words in chat messages.  Even if your text is not clean, your writing style can give you away.”   researcher Sadia Afroz said at the 29C3 Chaos Communication Congress in Germany.

The analysis methods could also expose botnet owners, malware authors and provide insight into the size and scope of underground markets, making the research appealing to law enforcement agencies.

“To achieve their results the researchers used techniques includingstylometric analysis, the authorship attribution framework Jstylo, andLatent Dirichlet allocation which can distinguish a conversation on stolen credit cards from one on exploit-writing, and similarly help identify interesting people.” reports SCMagazine.

 The research was practiced across millions of posts from tens of thousands of users including a series of multilingual underground websites including sites like the thebadhackerz.com, blackhatpalace.com, www.carders.cc, free-hack.com, hackel1te.info, hack-sector.forumh.net, rootwarez.org, L33tcrew.org and antichat.ru.

About FastFlux

Owner of ZeroSecurity, interested in programming, malware analysis and penetration testing. If you would like to write for the ZeroSecurity team, please use the contact form above.

Check Also

Amazon hacked – hacker leaks 80,000 login credentials

A hacker going by the name 0x2Taylor has said to have breached the servers of …