Michal Sofka is a Technical Leader in Cisco's Security Business Group. His research focuses on large scale machine learning for threat defense. He is interested in building robust data analytics applications in various domains.
Prior to Cisco, Michal was a research scientist and R&D manager at Siemens Corporation, Corporate Research (SCCT), Princeton, NJ. Michal did his undergraduate work at the Czech Technical University. He received the MS degree in Electrical Engineering from Union College in 2001. He received the MS and PhD degrees in Computer Science from the Rensselaer Polytechnic Institute (RPI) in 2006 and 2008, respectively.
PhD Position Opening in Machine Learning for Cybersecurity
Applications are invited for a PhD position at the Agents Technology Center, Department of Computer Science, Czech Technical University in Prague in the area of machine learning for cybersecurity. The lab boats over 30 research scientists (graduate students, post-docs, research faculty) and provides a unique interdisciplinary research environment with internationally recognized collaborators from Machine Learning, Cybersecurity, and Mathematical Modeling. The position entails research in machine learning for cybersecurity applications with particular focus on detecting and classifying advanced persistent threats, in collaboration with researchers from Cisco Systems. The candidate will benefit from mentorship of diverse research and threat analytics teams and will be exposed to cutting-edge technology, state-of-the-art infrastructure, and large real-world up-to-date datasets.
The candidate will work in the emerging area at the intersection of machine learning and cybersecurity. Prospective candidates should have mathematical background and excellent programming skills. Prior experience in network security is an advantage but not required.
Traditional approaches in network security rely on extracting communication patterns that are distinctive for malware. The pattern matching is efficient but it is hard to keep these systems up-to-date due to constantly changing malware. Behavioral techniques extract generic features to build detectors and classifiers that generalize to particular behavior of a malware family. Machine learning techniques are increasingly used to learn these behaviors, although there are new challenges not found in other domains, such as image analysis, natural language understanding, or text modeling.
April 30th with possible extension for exceptional candidates.
Please email your CV with research interests to:
Michal Sofka, PhD
Research Fellow, CTU Prague
Technical Leader, Cisco Systems