Intrusion Detection System by Using Data Mining Based On Class-Association-Rule Mining Using Genetic Network Programming

Computer Engineering

Consistently, there is the need to reestablish an installation of Intrusion Detection System (IDS) due to new attack methods or upgraded computing environments. Since many current IDSs are constructed by manual encoding of expert knowledge, changes to IDSs are expensive and slow. This paper describes a data mining framework for adaptively building Intrusion Detection (ID) models. Now security is considered as a major issue in networks, since the network has extended dramatically. Therefore, intrusion detection systems have attracted attention, as it has an ability to detect intrusion accesses effectively. These systems identify attacks and react by generating alerts or by blocking the unwanted data/traffic. The proposed system includes fuzzy logic with a data mining method which is a class-association rule mining method based on genetic algorithm. Due to the use of fuzzy logic, the proposed system can deal with mixed type of attributes and also avoid the sharp boundary problem. Genetic algorithm is used to extract many rules which are required for anomaly detection systems. An association-rule-mining method is used to extract a sufficient number of important rules for the user’s purpose rather than to extract all the rules meeting the criteria which are useful for misuse detection. Experimental results with KDD99Cup database from MIT Lincoln Laboratory show that the proposed method provides competitively high detection rates compared with crisp data mining.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.