Development of an Abridging Algorithm for Intrusion Detection System

Abstract

An intrusion detection system (IDS) is a system that monitors network traffic for suspicious activity and issues alerts when such activity is discovered. While anomaly detection and reporting is the primary function, some intrusion detection systems are capable of taking actions when malicious activity or anomalous traffic is detected, including blocking traffic sent from suspicious IP addresses. There are so many challenges occur in IDS like Network Traffic Dataset is Imbalanced i.e. there are few anomalous connections as compared to normal connections. Network Traffic Dataset is huge, High False Alarm rate and High Intrusion Detection Time. This thesis focuses on various issues like huge network traffic dataset i.e. large number of instances, large feature set, low accuracy and high rate of false alarms. With the help of feature selection technique relevant features are extracting. Propose technique helps to reduce the number of instances of dataset. The aim of this thesis is to enhance training time as well as memory requirement for processing and storage.