作者: Weizhi Meng , Wenjuan Li , Lam-For Kwok
DOI: 10.1016/J.COSE.2014.02.006
关键词: Intrusion detection system 、 Data mining 、 Filter (video) 、 Network security 、 Matching (statistics) 、 Signature (logic) 、 False alarm 、 Blacklist 、 Network packet 、 Computer science
摘要: Abstract Signature-based network intrusion detection systems (NIDSs) have been widely deployed in current security infrastructure. However, these suffer from some limitations such as packet overload, expensive signature matching and massive false alarms a large-scale environment. In this paper, we aim to develop an enhanced filter mechanism (named EFM ) comprehensively mitigate issues, which consists of three major components: context-aware blacklist-based filter, exclusive component KNN-based alarm filter. The experiments, were conducted with two data sets environment, demonstrate that our proposed can overall enhance the performance signature-based NIDS Snort aspects filtration, improvement reduction without affecting security.