In recent years, with the growing size and the importance of computer networks, it is very necessary to provide adequate protection for users data from snooping through the use of one of the protection techniques: encryption, firewall and intrusion detection systems etc. Intrusion detection systems is considered one of the most important components in the computer networks that deal with Network security problems. In this research, we suggested the intrusion detection and classification system through merging Fuzzy logic and Artificial Bee Colony Algorithm. Fuzzy logic has been used to build a classifier which has the ability to distinguish between the behavior of the normal user and behavior of the intruder. The artificial bee colony algorithm has been used to build the classifier which was used to classify the intrusion into one of the main types (DoS, R2L , U2R, Prob). The proposed system has the ability to detect and classify intrusion at high speed with a small percentage of false alarms as well as to detect the new attacks. The NSL-KDD dataset used in the training and testing the proposed system.The results of experiments showed that the efficiency of the proposed system performance were (97.59%) for the intrusion detection, and (0.12%) for the false alarms. Also, the Classification rates for classes (DoS, R2L,U2R,Prob) were (97.19, 77.09, 98.43, 93.23) Respectively, which is considered a superior performance comparing with other methods in the literature.
The estimation process is one of the pillars of the statistical inference process as well as the hypothesis test, and the assessment is based on the collection of information and conclusions about the teacher or the community's teachers on the basis of the result
