Intrusion Detection System Using Hybrid Detection Approach
| dc.contributor.advisor | Ejigu, Dejene (PhD) | |
| dc.contributor.author | Zewdu, Meheret | |
| dc.date.accessioned | 2018-06-21T07:01:09Z | |
| dc.date.accessioned | 2023-11-29T04:05:43Z | |
| dc.date.available | 2018-06-21T07:01:09Z | |
| dc.date.available | 2023-11-29T04:05:43Z | |
| dc.date.issued | 2015-04 | |
| dc.description.abstract | Due to the rapid growth of computer system and Internet, network security became crucial issue for most organizations. Mostly organizations increase usage of different tools and methods to secure their network due to the increase of security threats. Many methods have been developed to secure computer networks and communication over the Internet. However, none of the existing methods developed by different researches have an accuracy of detecting attacks with high detection rate and low false alarm rate. The other thing is most deal with single detection approach with high number of features which is challenging and time consuming to implement. Also it will examine only either previously known attacks or unknown attacks. This thesis work is devoted to solve those problems using intrusion detection system architecture that is based on neural network, signatures and dimension reduction that can promptly detect and classify attacks, whether they are known or never seen before. The proposed hybrid intrusion detection system combines signature based and anomaly based techniques. Signature based open source which uses pattern search for attack detection and the anomaly based system is developed using machine learning technique. We implemented dimension reduction using dataset NSL-KDD and train the system using the well known artificial neural network algorithm in the area of intrusion detection. The evaluation of performance and implementation of the proposed hybrid intrusion detection system are made with Java programming language using NetBeans. The results obtained by the implementation and evaluation are measured in comparison with other works done using single detection approach. The result shows that the output is encouraging and further refinement of the work can produce more robust and reliable intrusion detection system. Keywords: Hybrid, Intrusion Detection, Anomaly Detection, SNORT, Artificial Neural Network, Principal Component Analysis | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/123456789/2498 | |
| dc.language.iso | en | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | Hybrid; Intrusion Detection; Anomaly Detection; Snort; Artificial Neural Network; Principal Component Analysis | en_US |
| dc.title | Intrusion Detection System Using Hybrid Detection Approach | en_US |
| dc.type | Thesis | en_US |