作者: Pradeep Kannadiga , Mohammad Zulkernine , Anwar Haque
DOI: 10.1007/978-3-540-75496-1_3
关键词: Host-based intrusion detection system 、 Robust random early detection 、 Penetration (warfare) 、 Network security 、 Data mining 、 Event (computing) 、 Set (abstract data type) 、 Anomaly-based intrusion detection system 、 Intrusion detection system 、 Computer science
摘要: Intrusion detection systems (IDSs) can detect and respond to various attacks. However, they cannot all attacks, are not capable of predicting future In this research, we propose an automatic intrusion prediction system (IPS) called E-NIPS (Event-based Network Prediction System) that only attacks but also predict probable We have utilized network penetration scenarios partitioned into multiple phases depending on the sequences follow during penetrations. Each these consists attack classes precursors next phase. An class is a set same objectives, categorized generalize reduce burden engine alerts correlation tasks. Future predicted based detected in earlier phase scenario. Automatic provides little very crucial time required for fortifying networks against warns administrators about possible reduces damage caused due paper, describe architecture, operation, implementation E-NIPS. The prototype evaluated some most commonly occurring scenarios. experimental results show automatically useful information occurrence events.