作者: Anazida Zainal , Mohd Aizaini Maarof , Siti Mariyam Shamsuddin , Ajith Abraham , None
DOI: 10.1109/IAS.2008.35
关键词: Adaptive neuro fuzzy inference system 、 Artificial intelligence 、 Genetic programming 、 Random forest 、 Computer science 、 Ensemble learning 、 Statistical classification 、 Intrusion detection system 、 Data mining 、 False alarm 、 Machine learning 、 Ensemble forecasting
摘要: To achieve high accuracy while lowering false alarm rates are major challenges in designing an intrusion detection system. In addressing this issue, paper proposes ensemble of one-class classifiers where each uses different learning paradigms. The techniques deployed model are; linear genetic programming (LGP), adaptive neural fuzzy inference system (ANFIS) and random forest (RF). strengths from the individual models were evaluated rule was formulated. Empirical results show improvement for all classes network traffic; normal, probe, DoS, U2R R2L. RF, which is technique that generates many classification trees aggregates result also able to address imbalance dataset problem machine fail sufficiently it.