Skip to content

Reduced complexity attack characterisation using discriminant functions for the Gaussian distribution

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationInternational Conference on Visual Information Engineering (VIE 2003) Guildford, UK
Publisher or commissioning bodyInstitution of Electrical Engineers (IEE)
Publication dateJul 2003
Pages190 - 193
Number of pages4
ISBN (Print)0852967578
DOIs
StatePublished

Conference

ConferenceInternational Conference on Visual Information Engineering
CountryUnited Kingdom
CityGuildford
Period1/07/03 → …

Abstract

In this paper we describe a reduced complexity attack characterisation technique. A Bayesian framework is constructed, and the underlying distributions are assumed Gaussian. This allows quadratic discriminant functions to be used. This technique has the advantage over previous non-parametric techniques that histograms derived from Monte Carlo simulations are not necessary. Instead, only the mean and covariance matrix are required for each attack. This allows the number of features to the classifier to be increased providing superior classification performance without posing significant memory or computational requirements. We also show that in many cases the improvements in performance due to not having a fixed histogram bin size or issues with histogram sparsity outweigh the disadvantages due to a mismatch between the model and the observed data

Additional information

Rose publication type: Conference contribution Sponsorship: This work is supported by Motorola, the Metropolitan Police and EPSRC grant GM/M81885 Other identifier: Conf. Publ. 495

Event

International Conference on Visual Information Engineering

Duration1 Jul 2003 → …
CountryUnited Kingdom
CityGuildford

Event: Conference

View research connections

Related faculties, schools or groups