An Efficient Fuzzy Based Multi Level Clustering Model Using Artificial Bee Colony For Intrusion Detection

Abstract

Network security is becoming increasingly important as computer technology advances. One of the most important components in maintaining a secure network is an Intrusion Detection System (IDS). An IDS is a collection of tools used to detect and report network anomalies. Threats to computer networks are increasing at an alarming rate. As a result, it is critical to create and maintain a safe computing environment. For network security, researchers employ a range of technologies, including anomaly-based intrusion detection systems (AIDS). These anomaly-based detections face a major challenge in the classification of data. Optimization algorithms that mimic the foraging behavior of bees in nature, such as the artificial bee colony algorithm, is a highly successful tool. A computer network's intrusion detection system (IDS) is an essential tool for keeping tabs on the activities taking place in the network. Artificial Bee Colony (ABC) algorithm is used in this research for effective intrusion detection. More and more intrusion detection systems are needed to keep up with the increasing number of attacks and the increase in Internet bandwidth. Detecting developing threats with high accuracy at line rates is the prerequisite for a good intrusion detection system. As traffic grows, current systems will be overwhelmed by the sheer volume of false positives and negatives they generate. In order to detect intrusions based on anomalies, this research employs an Efficient Fuzzy based Multi Level Clustering Model using Artificial Bee Colony (EFMLC-ABC). A semi-supervised intrusion detection method based on an artificial bee colony algorithm is proposed in this paper to optimize cluster centers and identify the best clustering options. In order to assess the effectiveness of the proposed method, various subsets of the KDD Cup 99 database were subjected to experimental testing. Analyses have shown that the proposed algorithm is suitable and efficient for intrusion detection system.