Real-Time Network Intrusion Detection System Using Deep Learning

EasyChair Preprint 14016

Abstract

In recent years, the increasing complexity and sophistication of network attacks have posed significant challenges to traditional intrusion detection systems (IDS). To address these challenges, this study proposes a real-time network intrusion detection system that leverages deep learning techniques. The system utilizes a deep neural network architecture, specifically a convolutional neural network (CNN), to effectively learn and classify network traffic patterns associated with various types of intrusions.

The proposed system operates in real-time, continuously monitoring network traffic and identifying potential intrusions as they occur. By leveraging the power of deep learning algorithms, the system can automatically extract high-level features from raw network data, enabling accurate and efficient intrusion detection. The CNN model is trained using a large dataset of labeled network traffic, encompassing both normal and malicious activities.

To evaluate the performance of the system, extensive experiments are conducted using well-known benchmark datasets, including NSL-KDD and CICIDS2017. The results demonstrate that the proposed deep learning-based intrusion detection system achieves superior performance compared to traditional rule-based methods. The system exhibits high accuracy, low false positive rates, and fast response times, making it suitable for real-time deployment in large-scale network environments.

Keyphrases: Traffic, monitoring, network

@booklet{EasyChair:14016,
  author    = {Kaledio Potter and Ralph Shad},
  title     = {Real-Time Network Intrusion Detection System Using Deep Learning},
  howpublished = {EasyChair Preprint 14016},
  year      = {EasyChair, 2024}}