Learning Vector Quantization and Radial Basis Function Performance Comparison Based Intrusion Detection System

Information system’s technologies increase rapidly and continuously due to the huge traffic and volume of data. Stored data need to be secured adequately and transferred safely through the computer network. Therefore the data transaction mechanism still exposed to the intrusion attack of which consequences remain unlikable. An intrusion can be understood as a set of actions that can compromise the three security purposes known as Confidentiality, Integrity and Availability (CIA) of resources and services. In order to face on these intrusions, an efficient and robust Intrusion Detection System (IDS) which can detect successfully the intrusion is strongly recommended. An IDS is a network/host security tool used for preventing and detecting malicious attacks which could make a system useless. The purpose of this paper is to implement network intrusion detection system based on machine learning using Artificial Neural Network algorithms specifically the Learning Quantization Vector and Radial Basis Function make the comparison on the performance between these two algorithms.