Deep Learning Network Intrusion Detection with the Conv1d-Lstm Model: Integrating CNN and LSTM For Superior Performance

Abstract

Increased cases of cyber-attack and the rising levels of sophistication presents a significant threat to corporate networks, resulting in potential data breaches, financial losses, and reputational harm. Traditional Intrusion Detection Systems, which rely on predefined signatures and rules, have proven inadequate due to high false positive and false negative rates. This study introduces an innovative AI-based intrusion detection model to enhance corporate network security leveraging on deep learning techniques. The objective was to propose a Conv1d-LSTM Model, integrating convolutional neural networks (CNN) and recurrent neural networks (RNN) to analyze network traffic data from the CSE-CIC-IDS-2018 dataset, which encompasses a wide array of attack types, and provides a realistic representation of modern network traffic. This deep learning model effectively detects complex patterns and temporal dependencies in the data. The performance of the innovated model was evaluated using precision, accuracy, recall, and F1 score, to demonstrate its superior detection capabilities compared to conventional Intrusion Detection Systems (IDS). Additionally, a comparative analysis of CNN and RNN performance on the same dataset was conducted, highlighting the strengths and limitations of each approach. This research underscores the importance of integrating advanced AI methodologies into IDS frameworks to protect corporate networks from cyber threats.