Intrusion Detection System Enhanced by Hierarchical Bidirectional Fuzzy Rule Interpolation
Shangzhu Jin, Yanling Jiang, Jun Peng · 2018
Intrusion detection system (IDS) is used to find malicious connections and protect networks from external or internal attacks. Various fuzzy or fuzzy intelligence approaches have been proposed in the development of IDS. In particular, the fuzzy interpolation technique guarantees the performance of IDS where only a sparse rule base is available. Furthermore, backward fuzzy interpolation allows interpolation to be carried out when certain antecedents of observation variables are absent, whereas conventional methods do not work. In this paper, a novel fuzzy association rules based classification intrusion detection system framework enhanced by a hierarchical bidirectional fuzzy rule interpolation technique is proposed for designing an IDS. Hierarchical bidirectional fuzzy rule interpolation is also employed to refine fuzzy rule base while which exists some consistency. This framework uses fuzzy association rules for building classifiers, and allows the generation of security alerts from situations which are not directly covered, missing values, or existing inconsistency by knowledge base. The proposed method is herein applied through integration with the Snort software to demonstrate the efficacy of this proposed approach.