Intelligent Adaptive Intrusion Detection Systems Using Neural Networks (Comparitive Study)

Intrusion Detection Systems (IDSs) provide an important layer of security for computer systems and networks, and are becoming more and more necessary as reliance on Internet services increases and systems with sensitive data are more commonly open to Internet access. An IDS's responsibility is to detect suspicious or unacceptable system and network activity and to alert a systems administrator to this activity. Classification algorithms are used to discriminate between normal and different types of attacks. In this paper, a comparative study between the performances of recent nine Artificial Neural Networks (ANNs) based classifiers is evaluated, based on a selected set of features. The results showed that; the Multilayer Perceptrons (MLPS) based classifier provides the best results; about 99.63% true positive attacks are detected.