BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data science approaches to understanding key actors on online hack
 ing forums - Sergio Pastrana/Andrew Caines\, Computer Laboratory\, Univers
 ity of Cambridge
DTSTART:20180508T130000Z
DTEND:20180508T140000Z
UID:TALK99469@talks.cam.ac.uk
CONTACT:Alexander Vetterl
DESCRIPTION:Underground forums contain many thousands of active users\, bu
 t the vast majority will be involved\, at most\, in minor levels of devian
 ce. The number who become engaged in serious criminal activity is small. T
 hat being said\, underground forums have played a significant role in seve
 ral recent high-profile cybercrime activities. We have compiled a massive 
 dataset\, dubbed CrimeBB\, by crawling and scraping an assortment of onlin
 e forums. The dataset presents a unique opportunity to understand these co
 mmunities at scale\, and allows for longitudinal social data analysis. Man
 ual analysis is infeasible\, and the complexity of these forums\, and the 
 unique lexicon used\, makes automatic analysis challenging. In this talk w
 e will describe the data collection and present preliminary results obtain
 ed in the scope of an interdisciplinary project\, where we apply various d
 ata science methods to analyse the data. Concretely we apply social networ
 k analysis to analyse their social interests\, natural language processing
  to classify the type of information posted and clustering to group the ac
 tors based on forum activity.
LOCATION:LT2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR