CyLab Seminar: Tudor Dumitraș
February 13, 2023
12:00 p.m. ET
HBH A301 (lower level of Hamburg Hall) or Zoom
Please note this CyLab seminar is open only to Carnegie Mellon University faculty, students and staff.
Speaker: Tudor Dumitraș, Associate Professor, Electrical and Computer Engineering, Maryland Cybersecurity Center, UMIACS and CMU alumni
Talk Title: What can security and machine learning teach each other?
Abstract: When we apply machine learning to security tasks (e.g. malware detection), we often adopt off-the-shelf techniques that were developed for other domains, which have their own unique constraints. When we study the security of machine learning, we often focus on artificial threat models (e.g. adversarial examples) that may not capture the capabilities and limitations of real adversaries. Moreover, the two fields seem radically at odds with each other, because machine learning is not designed to operate under continuous adversarial pressure, which is inevitable in the security domain.
In this talk Tudor will draw on examples from both fields to argue that this tension also provides an opportunity for making progress. Anti-virus tools used to combat malware in the real world have implemented machine learning techniques for over a decade, while facing the adversarial pressure that occurs naturally in this setting. We can learn from this experience to model security-specific constraints, to assess their impact on machine learning, and ultimately to propose evidence-driven solutions to these challenges. In turn, understanding the effect of natural adversarial pressure on ML-based security tasks may yield more realistic threat models and a fresh perspective on the generalization gap in machine learning.
Bio: Tudor Dumitraș is an associate professor in the Department of Electrical and Computer Engineering with a joint appointment in the University of Maryland Institute for Advanced Computer Studies. He is also a core faculty member in the Maryland Cybersecurity Center. Dumitraș's research focuses on Big Data approaches to problems in system security and dependability.
In his previous role at Symantec Research Labs he built the Worldwide Intelligence Network Environment (WINE)—a platform for experimenting with Big Data techniques. Dumitraș received an honorable mention in the NSA competition for the Best Scientific Cybersecurity Paper of 2012. He also received the 2011 A. G. Jordan Award from the ECE Department at Carnegie Mellon University, the 2009 John Vlissides Award from ACM SIGPLAN, and the Best Paper Award at ASP-DAC'03.
Dumitraș received his doctorate in electrical and computer engineering from Carnegie Mellon University.