As it is well known, some Intrusion Detection Systems (IDSs) suffer from high rates of false positives and negatives. A mutation technique is proposed in this study to test and evaluate the performance of a full range of classifier ensembles for Network Intrusion Detection when trying to recognize new attacks. The novel technique applies mutant operators that randomly modify the features of the captured network packets to generate situations that could not otherwise be provided to IDSs while learning. A comprehensive comparison of supervised classifiers and their ensembles is performed to assess their generalization capability. It is based on the idea of confronting brand new network attacks obtained by means of the mutation technique. Finally, an example application of the proposed testing model is specially applied to the identification of network scans and related mutations
