A New Intelligent Intrusion Detection Method Based on Attribute Reduction and Parameters Optimization of SVM

Intelligent algorithms applied in intrusion detection system has become a tendency in recent years. An intelligent intrusion detection method is presented, based on rough set theory (RST) and improved binary particle swarm optimization with supported vector machine (IBPSO-SVM), which is combined attribute reduction with parameters optimization. Experiments on KDD CUP'99 dataset show this method can be an effective way for intrusion detection, not only accelerating the training time, but also improving the accuracy of test.