A Novel Intelligent Ensemble Classifier for Network Intrusion Detection System
| Autor: | M. A. Jabbar, Kankanahalli Srinivas, S. Sai Satyanarayana Reddy |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Boosting (machine learning)
Computer science business.industry Network security Decision tree learning Linear classifier 04 agricultural and veterinary sciences 02 engineering and technology Intrusion detection system Machine learning computer.software_genre Naive Bayes classifier Information sensitivity ComputingMethodologies_PATTERNRECOGNITION 040103 agronomy & agriculture 0202 electrical engineering electronic engineering information engineering 0401 agriculture forestry and fisheries 020201 artificial intelligence & image processing Artificial intelligence business computer Classifier (UML) Computer Science::Cryptography and Security |
| Zdroj: | Advances in Intelligent Systems and Computing ISBN: 9783319606170 SoCPaR |
| DOI: | 10.1007/978-3-319-60618-7_48 |
| Popis: | The objective of this research paper is to propose a novel ensemble Intrusion Detection System (IDS) to classify intrusions. Network security is important and challenging, as there is a tremendous growth of network-based services and sensitive information shared on the network. Intrusion detection system (IDS) is a security mechanism used to detect, prevent unauthorized access to computer networks. IDS plays a vital role in maintaining the secure network. Therefore there is a need to develop reliable and robust IDS. Various data mining techniques are used to implement network intrusion detection. Recently, ensemble classifiers are used to implement it. A group of classifiers known as ensemble classifiers outperforms base classifiers. This paper deals with a novel ensemble classifier based on naive Bayes and ADTree for intrusion detection. ADTree is a well known supervised boosting decision tree algorithm. Naive bayes is a linear classifier and assumes that all features are independent. Naive Bayes will not perform well, where complex attribute dependencies are present. The proposed ensemble combines ADTree and Naive Bayes to improve classification accuracy of the detection system. Our experimental results show that the proposed ensemble classifier outperforms other classifiers in terms of accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|