A comparative analysis of Feed-forward neural network & Recurrent Neural network to detect intrusion

As computer networks are grows exponentially security in computer system has become a foremost issue. Monitoring atypical activity can be one way to detect any violation that impedes computer systems security. Existing methods like statistical models [12] for intrusion detection not perform well whereas Neural network has been proved as an efficient method for intrusion detection [10]. In this paper Feed-forward and Recurrent Neural network is trained by Back propagation training algorithm and using normal data. Performances of these Neural Networks are compared against both normal data and intrusive data.