Design of a Bottleneck Layered DNN Algorithm for Intrusion Detection System

Abstract

Deep learning algorithms are very effective in the application of classification and prediction over the traditional estimators. The proposed work employs a bottleneck layer algorithm on CICIDS-2017 dataset to prove its efficacy on the prediction of cyber-attacks. The performance of the bottleneck model architecture is incorporated with Artificial Neural Network (ANN) and Deep Neural Network (DNN) models and compared over the traditional ANN, DNN and Support Vector Machines (SVM) models. The experimental work reaches a maximum accuracy of 92.35% in the DNN and 90.98% in ANN algorithm respectively.