Evolving Intrusion Detection Systems

Abstract

An Intrusion Detection System (IDS) is a program thatanalyses what happens or has happened during anexecution and tries to find indications that thecomputer has been misused. An IDS does not eliminatethe use of preventive mechanism but it works as thelast defensive mechanism in securing the system. Weevaluate the performances of two Genetic Programmingtechniques for IDS namely Linear Genetic Programming(LGP) and Multi-Expression Programming (MEP). Resultsare then compared with some machine learning techniqueslike Support Vector Machines (SVM) and Decision Trees(DT). Empirical results clearly show that GP techniquescould play an important role in designing real timeintrusion detection systems.