IEEE Winnipeg Section

IEEE

UofM ECE Department Seminar

generic_ece

Title:

Anomaly Detection as applied to Network
Intrusion Detection

Date:

Friday, March 8, 2013 at 1:30pm

Location:

E2-320 EITC Building, University of Manitoba Fort Garry Campus

Speaker:

Dr. Colin Gilmore
TRTech Manitoba

Abstract:

This presentation is divided into two parts.

First, I will give an overview of microwave tomography, or more generally electromagnetic imaging. Microwave tomography allows one to image the interior of objects which are normally obscured from human perception. The physics of the imaging experiment result in a non-linear imaging problem, which must be solved through optimization techniques. The nature of this imaging problem has driven and enriched the computational algorithms used to solve electromagnetic problems, as well as both microwave and computer hardware design. Using the appropriate computational techniques, both the electrical permittivity (related to the wave-speed in the target) and the electrical conductivity (related to the wave-decay in the target) can be simultaneously reconstructed in quantitative images. The ability to quantitatively image these parameters opens up many possibilities: applications range from oil-field exploration and development, to stored grain moisture conditions, to biomedical imaging and more. In this presentation, I will also show how it is possible to achieve image resolution an order of magnitude beyond the diffraction ‘limit’.

In the second part of this presentation, I will review the problem of detecting malicious behavior on computer networks through the use of an intelligent system based on anomaly detection algorithms. Fundamental considerations for this problem will be given, as well as a brief exposition of an anomaly detection algorithm. Finally, I will conclude with a discussion of future opportunities for research work in the area of information security.

Cost:

This will be a free event.

Contact:

For questions or more information: Lorraine Coates at 474-9099

Comments are closed.