Using Artificial Immune System on Implementation of Intrusion Detection Systems

2009 ◽  
Author(s):  
Aref EshghiShargh
Keyword(s):  
Immune System ◽  
Intrusion Detection ◽  
Artificial Immune System ◽  
Intrusion Detection Systems ◽  
Artificial Immune ◽  
Detection Systems

Detection of Network Attacks With Artificial Immune System

2020 ◽  
pp. 41-58
Author(s):  
Feyzan Saruhan-Ozdag ◽  
Derya Yiltas-Kaplan ◽  
Tolga Ensari
Keyword(s):  
Principal Component Analysis ◽  
Immune System ◽  
Intrusion Detection ◽  
Artificial Immune System ◽  
Information Gain ◽  
Principal Component ◽  
Component Analysis ◽  
Intrusion Detection Systems ◽  
Artificial Immune ◽  
Detection Systems

Intrusion detection systems are one of the most important tools used against the threats to network security in ever-evolving network structures. Along with evolving technology, it has become a necessity to design powerful intrusion detection systems and integrate them into network systems. The main purpose of this research is to develop a new method by using different techniques together to increase the attack detection rates. Negative selection algorithm, a type of artificial immune system algorithms, is used and improved at the stage of detector generation. In phase of the preparation of the data, information gain is used as feature selection and principal component analysis is used as dimensionality reduction method. The first method is the random detector generation and the other one is the method developed by combining the information gain, principal component analysis, and genetic algorithm. The methods were tested using the KDD CUP 99 data set. Different performance values are measured, and the results are compared with different machine learning algorithms.

Sign in / Sign up

Export Citation Format

Share Document