Efficient Rule Generation for Cost-Sensitive Misuse Detection Using Genetic Algorithms

This paper presents a genetic algorithm (GA) for generating efficient rules for cost-sensitive misuse detection in intrusion detection systems. The GA employs only the five most relevant features for each attack category for rule generation. Furthermore, it incorporates the different costs of misclassifying attacks in its fitness function to yield rules that are cost sensitive. The generated rules signal an attack as well as its category. The GA is implemented and evaluated on the KDDCup 99 dataset. Its detection performance is comparable to the winners of the KDDCup 99 competition. However, the rules generated by our GA are short and amenable for real time misuse detection