Ant Tree Miner Amyntas: Automatic, Cost-Based Feature Selection for Intrusion Detection

Abstract:

Intrusion Detection Systems (IDSs) analyse network traffic to identify suspicious patterns which indicate the intention to compromise the system. Traditional detection methods are still the norm for commercial products promoting a rigid, manual, and static detection platform. This paper focuses on recent advances in machine learning by implementing the Ant Tree Miner Amyntas (ATMa) classifier within intrusion detection. The proposed ATMa use Ant Colony Optimisation and a cost-based evaluation function to automatically select features from a data set before inducing Decision Trees (DTs) that classify network data


AUTHORS

Photo of Frans Hendrik Botes

Department of Information Technology Cape Peninsula University of Technology Cape Town,
South Africa

Frans Hendrik Botes is a postgraduate student at Cape Peninsula University of Technology. He is a hobbyist hacker and has research interests in artificial intelligence and cyber security.

Photo of Dr. Louise Leenen

University of the Western Cape and Center for Artificial Intelligence Research Cape Town,
South Africa

Louise Leenen areas of specialization are Artificial Intelligence applications in Cyber Defence and mathematical modelling. She is currently an Associate Professor at the University of the Western Cape in South Africa. She is the Chair of the International Federation for Information Processing’s Working Group 9.10 on ICT Uses in Peace and War. Louise holds a PhD in Computer Science from the University of Wollongong in Australia.

Photo of Dr. Retha De La Harpe

Department of Information Technology Cape Peninsula University of Technology Cape Town,
South Africa

Dr. Retha De La Harpe is the acting Head of the IT Department in the Faculty of Informatics and Design at Cape Peninsula University of Technology. She earned both a bachelor’s degree in Informatics and a master’s degree from Rand Afrikaans University. She earned D.Tech (IT) qualification at Cape Peninsula University of Technology in 2009.  She is the South African Coordinator of the Informatics Development for Health in Africa (INDEHELA) international research network and was a National Research Fund grant holder for four years. She is author and co-author of several research funding proposals—including the South Africa Finland Partnership. Her main research interest concerns data quality implications in both business and healthcare contexts.

Journal of Information Warfare

The definitive publication for the best and latest research and analysis on information warfare, information operations, and cyber crime. Available in traditional hard copy or online.

Quick Links

View the latest issue of JIW.

Latest Edition

Purchase a subscription to JIW.

Subscribe

Keywords

C

C2
C2S
CDX
CIA
CIP
CPS

D

DNS
DoD
DoS

I

IA
ICS

S

SOA

X

XRY

Quill Logo

The definitive publication for the best and latest research and analysis on information warfare, information operations, and cyber crime. Available in traditional hard copy or online.

SUBSCRIBE NOW

Get in touch

  • Journal of Information Warfare
    114 Ballard Street
    Yorktown, VA
    23690
  • 757.871.3949
  • jiw@gbpts.com