Deepsecure-IDS: A Deep Convolutional Learning Framework for High-Performance Network Intrusion Detection

Abstract

Recent advancements in network technology have led to the emergence of numerous sophisticated intrusion types that differ significantly from existing threats. Traditional firewalls cannot immediately detect these intrusions with their own set of rules and policies. Therefore, an Intrusion Detection System (IDS) is essential for safeguarding modern networks. The primary objective of this study is to develop an IDS capable of analyzing incoming and outgoing network traffic in real time for intrusion detection. The proposed method employs a Deep Convolutional Neural Network (DCNN) trained using 28 selected features from the NSL-KDD dataset. The deep learning (DL) pipeline comprises several phases for feature scaling and categorical data encoding before sending real-time data to the trained DCNN model for predictions. Particular information about the features of the NSL-KDD dataset is extracted using data that was sniffed from real-time network attack. The DL pipeline is located on a server that also houses the trained DCNN model and may be accessed. The DCNN's testing has produced exceptional results, with precision, accuracy, f1-score, and recall of 96%, 96%, 91%, and 92%, respectively. This study includes a thorough technical description of the system's implementation and operation. Furthermore, advanced IDSs that can detect contemporary intrusions can be built by utilizing the detailed descriptions offered in this work.