Machine learning to improve the performance of anomaly-based network intrusion detection in big data

With the rapid growth of digital technology communications are overwhelmed by network data traffic. The demand for internet is growing every day in today's cyber world, raising concerns about security. Big Data a term that describes vast volume complicated critical evaluating patterns and determining what has occurred network. Therefore, detecting attacks large challenging. Intrusion detection system (IDS) promising cybersecurity research field. In this paper, we proposed an efficient classification scheme IDS, which divided into two procedures, on CSE-CIC-IDS-2018 dataset, pre-processing techniques including under-sampling, feature selection, classifier algorithms were used to assess decide best performing model classify invaders. We have implemented compared seven machine learning with various criteria. This work explored application random forest (RF) selection conjunction (ML) linear regression (LR), k-Nearest Neighbor (k-NN), trees (CART), Bayes, RF, multi layer perceptron (MLP), XGBoost order implement IDSS. experimental results show MLP algorithm most successful performance evaluation matrix.