Title: Doppelganger Finder: Taking Stylometry To The Underground

Abstract: In this talk, I will discuss my lab's work in the emerging field 
of adversarial stylometry and machine learning. Machine learning algorithms 
are increasingly being used in security and privacy domains, in areas that 
go beyond intrusion or spam detection. For example, in digital forensics, 
questions often arise about the authors of documents: their identity, 
demographic background, and whether they can be linked to other documents. 
The field of stylometry uses linguistic features and machine learning 
techniques to answer these questions.

We have applied stylometry to difficult domains such as underground hacker
forums, open source projects (code), and tweets. In particular, I will discuss
our Doppelgänger Finder algorithm, which enables us to group Sybil accounts 
on underground forums and detect blogs from Twitter feeds. We also have 
developed a tool, Anonymouth, to help users understand their vulnerability 
to stylometric analysis and change their writing style. 

Bio: Rachel Greenstadt is an Associate Professor of Computer Science at Drexel
University, where she research the privacy and security properties of 
intelligent systems and the economics of electronic privacy and information 
security. Her work is at "layer 8" of the network—analyzing the content. She
is a member of the DARPA Computer Science Study Group and she runs the Privacy,
Security, and Automation Laboratory (PSAL) which is a vibrant group of ten 
researchers. The privacy research community has recognized her scholarship with 
the PET Award for Outstanding Research in Privacy Enhancing Technologies, the 
NSF CAREER Award, and the Andreas Pfitzmann Best Student Paper Award.