作者: Chaker Katar
DOI:
关键词: Intrusion detection system 、 Artificial neural network 、 Data mining 、 Decision tree 、 ALARM 、 Anomaly-based intrusion detection system 、 Engineering 、 Normal behaviour 、 Naive Bayes classifier 、 Overall performance
摘要: Summary Most intrusion detection systems (IDS) are based on a single algorithm that is designed to either model the normal behaviour patterns or attack signatures in network data traffic. often, these fail provide adequate alarm capability reduces false positive and negative rates. We here propose double multiple-model approach capable of enhancing overall performance IDS. In first step, every group identical models combined independently rest groups produce fused model. Then all final Our IDS adopted three reasoning methods: Naive Bayesian, Neural Nets, Decision Trees. used Darpa taxonomy KDD Intrusion Detection Dataset demonstrate working our