A Hybridization of Evolutionary Fuzzy Systems and Ant Colony Optimization for Intrusion Detection

A hybrid approach for intrusion detection in computer networks is presentedin this paper. The proposed approach combines an evolutionary-based fuzzysystem with an Ant Colony Optimization procedure to generate high-quality fuzzy-classication rules. We applied our hybrid learning approach to network security and validated it using the DARPA KDD-Cup99 benchmark dataset. The results indicate that in comparison to several traditional and new techniques, the proposed hybrid approach achieves better classicationaccuracies. The compared classication approaches are C4.5, Naffve Bayes,k-NN, SVM, Ripper, PNrule and MOGF-IDS. Moreover the improvementon classication accuracy has been obtained for most of the classes of the intrusion detection classication problem. In addition, the results indicate that the proposed hybrid system s total classication accuracy is 94.33% and its classication cost is 0.1675. Therefore, the resultant fuzzy classication rules can be used to produce a reliable intrusion detection system.