IBM Israel Research Seminars

www.sci.utah.edu Information Visualization aims to assist comprehension of vast amounts of high dimensional data and support the decision making process. In this talk I will present our novel visual correlation paradigm aimed to facilitate situational awareness. In particular I will focus on the process we followed in creating a solution to a specific and hard problem. I will then show how the scientific principles underlying our solution facilitated the generalization of our approach to a broader class of situational awareness domains. Situational awareness (SA) is the continuous extraction of environmental information, its integration with previous knowledge to form a coherent mental picture, and the use of that mental picture in anticipating future events. Network intrusion detection is an example of a prominent and, unfortunately, pervasive situation awareness problem.

The foundation of this work is based on what we term, the w3 premise, namely that each network event must have, at least, the three attributes: What, When and Where. I will first present our work on visual correlation of network intrusion events from disparate sources. I will then present two successive generalizations to the w3 premise that make our approach applicable to a much broader class of situational awareness problems. Finally, I will demonstrate the generality of our approaches by applying our visualization paradigm to a collection of diverse SA areas.

This work was done with the support and collaboration of the US Air Force Research Lab (AFRL) and the US Department of Defense (DOD).

About the speaker
Dr. Livnat is a research scientist at the Scientific Computing and Imaging Institute, (University of Utah). He had received his M.Sc. in Computer Science from the Hebrew University in Jerusalem and a Ph.D. in Computer Science from the University of Utah in 1999. In between, he served as a Captain in the Israeli Defense Forces (IDF) where he was a software team leader of a real-time search system. His work spans diverse research and development areas including computer graphics, scientific and information visualization, software architecture for both shared memory and distributed systems, high-order finite elements methods, CAGD, and computer generated holograms.