An Optimal NIDS for VCN Using Feature Selection and Deep Learning Technique

In this modern era, due to demand for cloud environments in business, the size, complexity, and chance of attacks virtual network (VCN) are increased. The protection VCN is required maintain faith users. Intrusion detection essential secure any network. existing approaches that use conventional neural cannot utilize all information identifying intrusions. paper, anomaly-based NIDS proposed. For feature selection, grey wolf optimization (GWO) hybridized with a bald eagle search (BES) algorithm. classification, deep learning approach - sparse auto-encoder (DSAE) employed. way, paper proposes model named GWO-DES-DSAE. proposed system simulated python programming environment. model's performance compared other recent both binary multi-class classification on considered datasets NSL-KDD, UNSW-NB15, CICIDS 2017 found better than methods.