Efficient algorithm for intrusion attack classification by analyzing KDD Cup 99

Importance of intrusion detection system (IDS) for network security management is widely accepted. Efficiency of IDS is mainly affected by algorithms used for feature identification and classification. Data mining can be very fruitful for feature selection and intrusion detection. In this paper, we have presented J48 classification algorithm for intrusion detection. To evaluate the performance of the algorithm correctly classified instances, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Root relative squared error and kappa statistics measures are applied.