TRUST Security Seminar: Machine Learning Under Attack

Seminar | March 19 | 1-2 p.m. | 240 Bechtel Engineering Center

 Eugene Vorobeychik, Vanderbilt University

 Team for Research in Ubiquitous Secure Technology (TRUST)

The success of machine learning, particularly in supervised settings, has led to numerous attempts to apply it in adversarial settings such as spam and malware detection. The core challenge in this class of applications is that adversaries are not static data generators, but make a deliberate effort to either evade the classifiers deployed to detect them, or degrade the quality of the data used to train the classifiers. I will discuss our recent research into the problem of adversarial classifier evasion, considering both the problem of adversarial (threat) modeling, and the defender's problem of hardening classifiers against evasion attacks. I will then describe some of our recent work in subset selection that is robust to denial-of-service attacks. Finally, I will describe our use of similar approaches for privacy-preserving data sharing.

Yevgeniy Vorobeychik is an Assistant Professor of Computer Science and Computer Engineering and Vanderbilt University. Previously, he was a Principal Member of Technical Staff at Sandia National Laboratories. Between 2008 and 2010 he was a post-doctoral research associate at the University of Pennsylvania Computer and Information Science department. He received Ph.D. (2008) and M.S.E. (2004) degrees in Computer Science and Engineering from the University of Michigan, and a B.S. degree in Computer Engineering from Northwestern University. His work focuses on game theoretic modeling of security and privacy, algorithmic and behavioral game theory and incentive design, optimization, complex systems, epidemic control, network economics, and machine learning. Dr. Vorobeychik has published over 75 research articles on these topics. Dr. Vorobeychik was nominated for the 2008 ACM Doctoral Dissertation Award and received honorable mention for the 2008 IFAAMAS Distinguished Dissertation Award. In 2012 he was nominated for the Sandia Employee Recognition Award for Technical Excellence. He was also a recipient of a NSF IGERT interdisciplinary research fellowship at the University of Michigan, as well as a distinguished Computer Engineering undergraduate award at Northwestern University.

This event is sponsored by The Center for Information Technology Research in the Interest of Society (CITRIS), the Institute of Transportation Studies (ITS) and The Team for Research in Ubiquitous Secure Technology (TRUST).

 General Public

 General Public

 Lunch is offered

 cawinter@berkeley.edu, 510-643-8425