Deep Neural Network Based Real-Time Intrusion Detection System

Abstract In recent years, due to the rapid growth in network technology, numerous types of intrusions have been uncovered that differ from existing ones, and conventional firewalls with specific rule sets policies are incapable identifying those real-time. Therefore, demands requirement a real-time intrusion detection system (RT-IDS). The ultimate purpose this research is construct an RT-IDS capable by analysing inbound outbound data proposed consists deep neural (DNN) trained using 28 features NSL-KDD dataset. addition, it contains machine learning (ML) pipeline sequential components for categorical encoding feature scaling, which used before transmitting DNN model make predictions. Moreover, extractor, C++ program sniffs traffic derives relevant related dataset sniffed data, deployed between gateway router local area (LAN). Together model, ML hosted server can be accessed via representational state transfer application programming interface (REST API). has revealed outstanding testing performance results achieving 81%, 96%, 70% 81% accuracy, precision, recall f1-score accordingly. This comprises comprehensive technical explanation concerning implementation functionality complete system. leveraging extensive explanations provided paper, advanced IDSs modern constructed.