Speaker:
Nandi Leslie
Raytheon

Abstract: Using semi-supervised learning, I propose an anomaly-based network intrusion detection system (NIDS) to detect and classify anomalous and/or malicious traffic. With this proposed machine learning approach, we detect botnet traffic and distinguish it from the normal and background traffic in the IPv4 flow datasets. I evaluate the prediction performance results for the flow-based NIDS algorithms. I show an improvement in detection accuracy and reduction in error rates, when compared with signature-based NIDS and previous studies.

About: Dr. Nandi Leslie is an Engineering Fellow at RaytheonTechnologies, serving as an Applied Mathematician andPrincipal Investigator at the U.S. Combat CapabilitiesDevelopment Command/Army Research Laboratory (ARL)customer, since 2015. She supports the Raytheon Intelligenceand Space business area and ARL on research and developmentprojects related to machine learning, and cyber andelectromagnetic activities. Dr. Leslie has published over 40papers in journal, conference proceedings, magazines, andgovernment technical reports on machine learning,cybersecurity, network resilience, submarine security, andmathematical biology with over 375 citations. She has givenover 30 research talks at national and international conferencesin both unclassified and classified settings

Before joining Raytheon, Dr. Leslie led and contributed to multi-target tracking projects at SystemsPlanning and Analysis, Inc. from 2007 to 2015. In this role, she served as Program Manager and SeniorOperations Research Analyst, and she developed modeling approaches for the U.S. Navy SubmarineSecurity Program, Office of the Secretary of Defense (OSD), and Joint Program Offices, using stochasticprocesses, to understand various tactical problems in different domains; such as submarine search anddetection in oceanographic and atmospheric environmental conditions for the Navy, and damageassessments and remediation of cyberattacks to the Defense Industrial Base for OSD. In addition, shespent two years as a Lecturer and Postdoctoral Researcher at the University of Maryland, College Park inDepartment of Mathematics from 2005 to 2007. She earned her Ph.D. in Applied and ComputationalMathematics from Princeton University in 2005, where her research focused on developing and analyzingspatially-explicit stochastic models of deforestation in forest ecosystems of the Neotropics.

The weekly security seminar has been held every semester since spring of 1992. We invite personnel at Purdue and visitors from outside to present on topics of particular interest to them in the areas of computer and network security, computer crime investigation, information warfare, information ethics, public policy for computing and security, the computing "underground," and other related topics. More info