Integrated Intrusion Detection System Using Soft Computing

Intrusion Detection systems are increasingly a key part of system defense. Various approaches to Intrusion Detection are currently being used but they are relatively ineffective. Among the several soft computing paradigms, we investigated genetic algorithms and neural networks to model fast and efficient Intrusion Detection Systems. With the feature selection process proposed it is possible to reduce the number of input features significantly which is very important due to the fact that the Radial Basis Function networks can effectively be prevented from over fitting. The Genetic algorithm employs only the eight most relevant features for each attack category for rule generation. The generated rules signal an attack as well as its category and it is end for training to RBF network. The optimal subset of features combined with the generated rules, can be used to analyze the attacks. Empirical results clearly show that soft computing approach could play a major role for intrusion detection. The model was verified on KDD99 demonstrating higher detection rates than those reported by the state of art while maintaining low false positive rate.