- All Journals
- Al-Qadisiyah University
- Basrah University
- Kirkuk University
- Mosul University
- The Iraqi Borad for Medical Specialization
- University of Anbar
- University of Technology
- Al Mustafa University
- Al-Zahraa University for Women
- Alnoor University
- Kunooz University
- Misan University
- Ninevah University
- Tikrit University
- University of Al-Hamdaniya
- University of Kerbala
Application of the Genetic Algorithm in the Network Intrusion Detection System Using NSL-KDD Data | ||
| AL-Rafidain Journal of Computer Sciences and Mathematics | ||
| Article 23, Volume 10, Issue 2, 2013, Pages 145-158 PDF (435.81 K) | ||
| Document Type: Research Paper | ||
| DOI: 10.33899/csmj.2013.163491 | ||
| Authors | ||
| Naglaa B. Ibrahim; Hana M. Usman | ||
| College of Computer Science and Mathematics University of Mosul, Mosul, Iraq | ||
| Abstract | ||
| With the development of the Internet, technological innovation and the availability of information emerged new computer security threats. The researchers are developing new systems known as Intrusion Detection Systems IDSs for detecting the known and unknown attacks. IDS have two approaches depending on the detecting theories: Misuse Detection and Anomaly Detection. This paper aims to design and implement a misuse network intrusion detection system based on Genetic Algorithm. The efficiency of using GA for building IDS based on NSL-KDD is verified. For rules generation NSL-KDD Data Set is used which include, KDDTrain and KDDTest, 125973 and 22544 records respectively, each record consists of 41 features and one class attribute for specifying normal and abnormal connection (complete train and test data are used), In order to get rid of redundancy and inappropriate features Principal Component Analysis (PCA) is used for selecting (5) features. Number of experiments have been done. The experimental results show that the proposed system based on GA and using PCA (for selecting five features) on NSL-KDD able to speed up the process of intrusion detection and to minimize the CPU time cost and reducing time for training and testing, that the detection rate: 91.6% and false alarm is: 0% and classification rate (DoS 93.48 %), (Normal 99.52%) , (Probe 81.16%), (R2L 69.47%), (U2R 32.84%). C# programming language is used for system implementation. | ||
| Keywords | ||
| genetic algorithm; Network Intrusion Detection System; NSL-KDD Data | ||
|
Statistics Article View: 342 PDF Download: 265 |
||