Optimizing a New Intrusion Detection System Using Ensemble Methods and Deep Neural Network

Abstract

In the previous, not many years, digital assaults have become a significant issue in cybersecurity. Researchers are taking a shot at the intrusion detection framework from the most recent couple of decades and numerous methodologies have been developed. Yet at the same time, these methodologies won't be adequate for the intrusion detection framework in the up and coming days. Along these lines, in light of headways in innovation, the current framework has to be refreshed with another one. In this paper, ensemble learning strategies have been examined for the intrusion detection system were boosting and bagging methods like Distributed Random Forest (DRF), Gradient Boosting Machine (GBM) and XGBoost are implemented using python library H2O for the new Intrusion identification framework. The Deep Neural Network (DNN) is likewise executed using the H2O library and found that our model beats the past aftereffect of Deep Neural Network (DNN) after utilizing the feature selection method genetic algorithm. Our outcomes outperform the numerous old-style machine learning models too.