Home // ICAS 2011, The Seventh International Conference on Autonomic and Autonomous Systems // View article

An Autonomic Security Mechanism Based on Novelty Detection and Concept Drift

Authors:
Gesiel Rios Lopes
André L. V. Coelho
Raimir Holanda Filho

Keywords: Autonomic network, autonomic element, novelty detection, concept drift.

Abstract:
The growth in the number of elements and services in current computer networks and the integration of several technologies, in order to provide connectivity and services everytime and everywhere, have renderede the computing infrastructure complex and susceptible to malicious activities. In this sense, the use of autonomic computing principles arises as an alternative to face these challenges, in special to deal with the development of security mechanisms capable of infering malicious activities with the purpose of self-protecting the infrastructure against attacks.This paper presents and evaluates a novel model of an autonomic element which is based on the notions of novelty detection and concept drift. The element is able to infer malicious activities that may compromise the proper functioning of the network. Experimental results, extracted from real samples network traffic, indicate that the element autonomic element infact is very useful.

Pages: 158 to 163

Copyright: Copyright (c) IARIA, 2011

Publication date: May 22, 2011

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-134-2

Location: Venice/Mestre, Italy

Dates: from May 22, 2011 to May 27, 2011