HDLNIDS: Hybrid Deep-Learning-Based Network Intrusion Detection System

Attacks on networks are currently the most pressing issue confronting modern society. Network risks affect all networks, from small to large. An intrusion detection system must be present for detecting and mitigating hostile attacks inside networks. Machine Learning Deep used in several sectors, particularly security of information, design efficient systems. These systems can quickly accurately identify threats. However, because malicious threats emerge evolve regularly, need an advanced solution. Hence, building that is both effective intelligent one cognizant research issues. There public datasets available detection. Because complexity continually evolving attack method, publicly databases updated frequently. A convolutional recurrent neural network employed this study construct a deep-learning-based hybrid detects over network. To boost efficiency predictability, performs convolution collect local features, while deep-layered extracts features proposed Hybrid Deep-Learning-Based Intrusion Detection System (HDLNIDS). Experiments conducted using accessible benchmark CICIDS-2018 data, determine effectiveness system. The findings demonstrate HDLNIDS outperforms current approaches with average accuracy 98.90% attacks.