Friday, September 28, 2007

Warning to Me

Freedom: It was wonderful....
You might think your anonymous online rants are oh-so-clever. But they'll give you away, too. A federally-funded artificial intelligence lab is figuring out how to track people over the Internet, based on how they write.

The University of Arizona's ultra-ambitious "Dark Web" project "aims to systematically collect and analyze all terrorist-generated content on the Web," the National Science Foundation notes. And that analysis, according to the Arizona Star, includes a program which "identif[ies] and track[s] individual authors by their writing styles."

That component, called Writeprint, helps combat the Web's anonymity by studying thousands of lingual, structural and semantic features in online postings. With 95 percent certainty, it can attribute multiple postings to a single author.

From there, Dark Web has the ability to track a single person over time as his views become radicalized.

The project analyzes which types of individuals might be more susceptible to recruitment by extremist groups, and which messages or rhetoric are more effective in radicalizing people.

The research comes with risks, according to the NSF.

Dark Web also uses complex tracking software called Web spiders to search discussion threads and other content to find the corners of the Internet where terrorist activities are taking place. But according to [Arizona's] Hsinchun Chen, sometimes the terrorists fight back.

"They can put booby-traps in their Web forums," Chen explains, "and the spider can bring back viruses to our machines." This online cat-and-mouse game means Dark Web must be constantly vigilant against these and other counter-measures deployed by the terrorists.

The Arizona group has been at this sort of research for a while, now -- sifting through more than 900,000 Islamist web pages. Here's a report Xeni filed last year for NPR on the Dark Web project. And here's a meaty blog post from Dancho Danchev on related projects.

Strangely, the Arizona AI lab's website seems to be down right now. But, thanks to the magic of Google, you can read a whole bunch of the the group's "Dark Web" research papers here. As the Star notes:

In one study, Chen found terrorist Web sites and U.S. government sites are equally sophisticated on the technical level. But terrorist Web sites are about 10 times richer in multi-media content like pictures and video and also about 10 times more effective in creating a community. Terrorist sites are quick to provide answers and instruction when their users ask questions, he said.
Link.

No comments: