Intrusion Detection System Using Back Propagation Neural Network and FFNN with Different Training Parameters

R. Sekhar and K. Thangavel

The study of Intrusion Detection Systems (IDSs) is unavoidable in the field of network security due to the present smart attacks for stealing vital data of an organization. Identifying attacks and normal traffic are much challenging, time consuming and highly technical. In existing works, the accuracy of intrusion detection in network traffic is different for different algorithms. This paper proposed a better intrusion detection system using Back Propagation Neural Network and Feed Forward Neural Network by training with different training parameters. The proposed system consists of five phases namely data collection, data conversion, data splitting for training and testing, pre-processing, training and testing. It produces better accuracy in detection process than the existing Feed forward Neural Network and Back Propagation algorithm. The NSL_KDD data set has been used for analyzing the proposed system.

Volume 11 | 04-Special Issue

Pages: 1661-1666