Development of PCCNN-Based Network Intrusion Detection System for EDGE Computing

Kamaledin Abodayeh,Kiran Shahzadi,Ali Raza,Muhammad Rafiq,Sana Sarwar,Muhammad Mohsin,Qasim Naveed,Badar Ul Zaman,Muhammad Shoaib Arif,Syed Zaheer Abbas,Zunir Zeb,Muhammad Naveed

doi:10.32604/cmc.2022.018708

Abstract

Intrusion Detection System (IDS) plays a crucial role in detecting and identifying the DoS and DDoS type of attacks on IoT devices. However, anomaly-based techniques do not provide acceptable accuracy for efficacious intrusion detection. Also, we found many difficulty levels when applying IDS to IoT devices for identifying attempted attacks. Given this background, we designed a solution to detect intrusions using the Convolutional Neural Network (CNN) for Enhanced Data rates for GSM Evolution (EDGE) Computing. We created two separate categories to handle the attack and non-attack events in the system. The findings of this study indicate that this approach was significantly effective. We attempted both multiclass and binary classification. In the case of binary, we clustered all malicious traffic data in a single class. Also, we developed 13 layers of Sequential 1-D CNN for IDS detection and assessed them on the public dataset NSL-KDD. Principal Component Analysis (PCA) was implemented to decrease the size of the feature vector based on feature extraction and engineering. The approach proposed in the current investigation obtained accuracies of 99.34% and 99.13% for binary and multiclass classification, respectively, for the NSL-KDD dataset. The experimental outcomes showed that the proposed Principal Component-based Convolution Neural Network (PCCNN) approach achieved greater precision based on deep learning and has potential use in modern intrusion detection for IoT systems.

Highlights

In the past decade, the world has witnessed a rapid growth in smart devices, with a rising focus on the Internet of Things (IoT)
The main contributions of the current research are: (i) We have proposed a new approach that combined the benefits of Principal Component Analysis (PCA) for feature collection and the deep learning-based Convolutional Neural Network (CNN) classifiers to ensure effectual and accurate intrusion detection in IoT environments
A solution was designed based on PCA and CNN (Convolutional neural network) to detect intrusion in Enhanced Data rates for GSM Evolution (EDGE) Computing

Summary

Introduction

The world has witnessed a rapid growth in smart devices, with a rising focus on the Internet of Things (IoT). All small and big devices such as computers, mobile phones, palmtops, smartwatches, and health bands are connected with the internet. They communicate with each other and form bridges to share information amongst them to perform a task. IoT helps resolve various issues for the users, aiding the development and communication of different kinds of digital devices. They ensure smoother and significantly improved lives with. Most IoT devices have restricted resources sufficient only for transferring data via the internet on the cloud for processing and storage. Near the IoT devices, [1] EDGE computing ensures temporary data storage and processing, which reduces the volume of information to be delivered on the cloud

Objectives

Methods

Findings

Conclusion