Intrusion Detection based on Ensemble Learning for Big Data Classification

Abstract Intrusion Detection Systems (IDS) plays a crucial role in the security of modern computer systems and networks. They continuously monitor the activity on a network, looking for any signs of unauthorized access or malicious behavior. Therefore, the main objective of developers is the improvement of Intrusion Detection Systems to control network security. Challenges of Big data in intrusion detection are a struggle that both researchers and developers face due to the decreased scalability of network data. Furthermore, Machine Learning has a crucial role in developing Network Intrusion Detection Systems (NIDS). Ensemble learning is a machine learning technique that combines the predictions of multiple individual models to produce a more accurate and stable prediction. It is considered to be more important than simply learning because it addresses several limitations of simple learning methods. In this work, an ensemble model is proposed to evaluate dimensionality minimization in an Intrusion Detection System and several combinations were tested as well as processed on datasets. Yet, to overcome Big Data challenges, the feature's effects on the datasets were determined and only the most effective ones were considered to significantly differentiate data. Thus, the ensemble model results were solved using standard evaluation measures. In addition, the experimentation proved that the tested ensemble models perform better than the existing models. Big Data techniques have been applied to treat and analyze massive Data to provide an insightful data analysis process.