The Distinguished Speaker Webinar Series is aimed at advancing the state-of-the-art concepts and methods in artificial intelligence and cyber security areas. The series is jointly hosted by the Centers for Cyber Security and AI Research and the School of Electrical Engineering and Computer Science (SEECS) at the University of North Dakota College of Engineering & Mines.
Speaker Biography:
Dr. Matt Wright is Endowed Professor and Chair of Cybersecurity at RIT. He earned his PhD in CS at the University of Massachusetts in 2005. His research interests include deepfake detection, applying AI to malware and traffic analysis, and understanding the human element of security. He has over 100 peer-reviewed publications, including many works appearing in top-tier venues in cybersecurity, human-computer interaction, and computer networks.
About the Webinar:
Attackers use steppingstones - intermediate hosts that they have compromised - to gain entry into well-protected networks while hiding their tracks. In this talk, we explore how traffic analysis with deep learning can be used to turn the use of this tactic against attackers. We brew up a cup of DeepCoFFEA and its upgraded version, ESPRESSO, designed for efficient and highly effective detection of stepping stones. DeepCoFFEA out grinds the prior state-of-the-art by two orders of magnitude, while ESPRESSO steams up the accuracy even higher, with over an 80% increase in True Positive Rate (TPR) at just 0.01% False Positive Rate (FPR).