Rachel Greenstadt, Assistant Professor, Department of Computer Science
Privacy & Stylometry: Exploring the Limitations and Potential
of Automated Authorship Recognition
Wednesday, September 7, 4:00 PM
Packard Lab room 466
Reception prior to talk in Packard Lobby
Abstract: The use of statistical AI techniques in authorship recognition (or stylometry) has contributed to literary and historical breakthroughs.These successes have led to the use of these techniques in criminal investigations and prosecutions. Stylometry, however, can also be used to infringe upon the privacy of individuals who wish to publish documents anonymously. Our research demonstrates how various types of attacks can reduce the effectiveness of stylometric techniques down to the level of random guessing and worse. Few have studied the introduction of adversarial attacks and their devastating effect on the robustness of existing classification methods. Our work in this area has shown that non-expert human subjects can defeat several representative stylometric methods simply by consciously hiding their writing style or imitating the style of another author. This talk will also examine the ways in which authorship recognition can be used to thwart privacy and anonymity and how these attacks can be used to mitigate this threat. It will also cover our current progress in establishing a large corpus of writing samples and attack data and the creation of a tool which can aid authors in preserving their privacy when publishing anonymously.
Bio: Rachel Greenstadt is an Assistant Professor in the Department of Computer Science at Drexel University in Philadelphia, PA. She received her B.S. and M.Eng from MIT (Cambridge, MA) in 2001 and 2001 and her Ph.D. from Harvard University (Cambridge, MA) in 2007. She leadsthe Privacy, Security, and Automation Laboratory at Drexel University (http://psal.cs.drexel.edu) where she has attracted a research team of PhD students, M.S. students and undergraduates with interests and expertise in information extraction, machine learning, agents, trust, and security. Her research interests are focused on designing more trustworthy intelligent systems, systems that act not only autonomously, but also with integrity, so that they can be trusted with important data and decisions. Her work on authorship recognition is sponsored by the DARPA Computer Science Study Group and Intel. Dr. Greenstadt recently chaired the 3rd Workshop (and is currently co-chair for the 4th) on Artificial Intelligence and Security at ACM CCS.