Classification Denial of Service (DOS) Attack using Artificial Neural Network Learning Vector Quantization (LVQ)

Reza Firsandaya Malik, Verlly Puspita

Abstract


Network security is an important aspect in computer network defense. There are many threats find vulnerabilities and exploits for launching attacks. Threats that purpose to prevent users get the service of the system is Denial of Service (DoS). One of software application that can detect intrusion on is an Intrusion Detection System (IDS). IDS is a defense system to detect suspicious activity on the network. IDS has ability to categorize the various types of attack and not attack. In this research, Learning Vector Quantization (LVQ) neural network is used to classify the type of attacks. LVQ is a method to study the competitive supervised layer. If two input vectors approximately equal, then the competitive layers will put both the input vector into the same class. The results show IDS able to classify PING and UDP Floods are 100%.

Keywords


Network Security, Denial of Service (DoS) , IDS , Learning Vector Quantization (LVQ)

References


K. Kumar, R. . Joshi and K. Singh, “An Integrated Approach for Defending against Distributed Denial-of-Service (DDoS) Attac s”, iriss, 2006, IIT Madras.

B. B. Gupta, "Distributed Denial of Service Prevention Techniques", International Journal of Computer and Electrical Engineering, Vol. 2, No. 2, April, 2010, 1793-8163

Jarmo Mölsä, "Mitigating denial of service attacks: A tutorial", Journal of Computer Security 13 (2005) 807–837

Reyadh Shaker Naoum and Zainab Namh Al-Sultani, " Learning Vector Quantization (LVQ) and k-Nearest Neighbor for Intrusion Classification", World of Computer Science and Information Technology Journal (WCSIT), Vol. 2, No. 3, 105-109, 2012

Atuti, Erna Dwi. 2009. Introduction Artificial Neural Network Theory and Aplication. Center Java: Star Publising.

Sven F. Crone, "forecasting with artificial neural networks", http://www.neural-forecasting.com/lvq_neural_nets.htm

Suganda, Dearby,”Design of Intrusion Detection System Using Self-Organizing Maps”, Sriwijaya University, 2012,Unpublished.

M. Moradi and M. Zulkernine, “A neural network based system for intrusion detection and classification of attacks”, In 2004 IEEE International Conference on Advances in Intelligent Systems.

Abdulkader A. Alfantookh, "DoS Attacks Intelligent Detection using Neural Networks", Journal of King Saud University - Computer and Information Sciences,Volume 18, 2006, Pages 31–51

Mohammed Salem and Helen Armstrong, “Identifying DoS Attac s Using Data attern Analysis”, roceedings of the 6th Australian Information Security Management Conference, Edith Cowan University, Perth, Western Australia, Ist to 3rd December 2006.

Gulay ¨ Oke, George Loukas, and Erol Gelenbe. "Detecting Denial of Service Attacks with Bayesian Classifiers and the Random Neural Network", In IEEE Fuzzy Systems Conference, London, 2007.

Bogdanoski, Mitko and Ale sandar Ristes i,”Wireless Network Behavior under ICMP Ping Flood DoS Attack and Mitigation Techniques”,Military Academy,Macedonia,2011.

Duraiswany and G. alenivel, “Intrusion Detection System in UDP Potocol”. King College of Engineering,2010.


Full Text: PDF

Refbacks

  • There are currently no refbacks.