Abstract | ||
---|---|---|
Intrusion detection systems (IDS) are an important element in a network's defences to help protect against increasingly sophisticated cyber attacks. IDS that rely solely on a database of stored known attacks are no longer sufficient for effectively detecting modern day threats. This paper presents a novel anomaly detection technique that can be used to detect previously unknown attacks on a network by identifying attack features. This effects-based feature identification method uniquely combines k-means clustering, Naive Bayes feature selection and C4.5 decision tree classification for pinpointing cyber attacks with a high degree of accuracy in order to increase the situational awareness of cyber network operators. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1016/j.neucom.2013.04.038 | Neurocomputing |
Keywords | Field | DocType |
high degree,decision tree classification,cyber network operator,sophisticated cyber attack,naive bayes feature selection,network intrusion detection,cyber attack,attack feature,effects-based feature identification,novel anomaly detection technique,effects-based feature identification method,intrusion detection system,decision trees,intrusion detection,classification,clustering,feature selection | Decision tree,Data mining,Anomaly detection,Feature selection,Computer science,Situation awareness,Anomaly-based intrusion detection system,Artificial intelligence,Cluster analysis,Intrusion detection system,Naive Bayes classifier,Pattern recognition,Machine learning | Journal |
Volume | ISSN | Citations |
121, | 0925-2312 | 20 |
PageRank | References | Authors |
0.76 | 39 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Panos Louvieris | 1 | 71 | 9.56 |
Natalie Clewley | 2 | 37 | 3.13 |
Xiaohui Liu | 3 | 5042 | 269.99 |