Confederation of FCM clustering, ANN and SVM techniques to implement hybrid NIDS using corrected KDD cup 99 dataset

With the rapid advancement in the network technologies including higher bandwidths and ease of connectivity of wireless and mobile devices, Intrusion detection and protection systems have become a essential addition to the security infrastructure of almost every organization. Data mining techniques now a day play a vital role in development of IDS. In this paper, an effort has been made to propose an efficient intrusion detection model by blending competent data mining techniques such as Fuzzy-C-means clustering, Artificial neural network(ANN) and support vector machine (SVM), which is significantly improvises the prediction of network intrusions. We implemented the proposed IDS in MATLAB version R2013a on a Windows PC having 3.20 GHz CPU and 4GB RAM. The experiments and evaluations of proposed method were performed with Corrected KDD cup 99 intrusion detection dataset and we used sensitivity, specificity and accuracy as the evaluation metrics. We attained detection accuracy of about 99.66% for DOS attacks, 98.55% for PROBE, 98.99% for R2L and 98.81% for U2R attacks. Results are compared with relevant existing techniques so as to prove efficiency of our model.