Network Intrusion Detection Using Weighted Voting Ensemble Deep Learning Model

System and network security have become one of the main considerations for the system or network design, implementation and maintenance. The increased volume of traffic and the ever-changing form of internet communications has led to a steep rise in network attacks, hence the need to protect both sides of the communication is essential. Over the last couple of years, an upsurge in the use of machine learning and deep learning techniques in detecting network attacks can be noticed. Alongside with individual machine and deep learning techniques, various ensemble techniques have been implemented in order to combine multiple models working on the same problem. However, ensemble techniques mostly focus on machine learning models, disregarding the fact that deep learning techniques have been proven to be efficient when handling large amounts of data. In this paper, a network intrusion detection system is implemented using a weighted voting ensemble deep learning model. Fifteen various Deep Neural Network models have been trained and evaluated on the imbalanced multiclass CICIDS-2017 dataset. Weighted voting system has been implemented for combining decisions of various models in two ways. The evaluation results for multiple combinations are given. The proposed system has the ability to use heterogeneous models for the decision.