Academic Journals Database
Disseminating quality controlled scientific knowledge

An Intelligent Intrusion Detection System Using Genetic Algorithms and Features Selection

ADD TO MY LIST
 
Author(s): Hossein M. Shirazi

Journal: Majlesi Journal of Electrical Engineering
ISSN 2008-1413

Volume: 4;
Issue: 1;
Start page: 33;
Date: 2010;
Original page

Keywords: Intrusion Detection Systems | anomaly detection | genetic algorithms | Features Selection

ABSTRACT
There has been a rapid growth in the numbers of attacks to the information and communication systems. Also, we witness smarter behaviors from the attackers. Thus, to prevent our systems from these attackers, we need to create smarter intrusion detection systems. In this paper, a new intelligent intrusion detection system has been proposed using genetic algorithms. In this system, at first, the network connection features were ranked according to their importance in detecting attack using information theory measures. Then, the network traffic linear classifiers based on genetic algorithms have been designed. These classifiers were trained and tested using KDD99 data sets. A detection engine based on these classifiers was build and experimented. The experimental results showed a detection rate up till to 92.94%. This engine can be used in real-time mode.
Why do you need a reservation system?      Affiliate Program