Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm
This paper addresses the critical security challenges in the internet of things (IoT) landscape by implementing an innovative solution that combines convolutional neural networks (CNNs) for feature extraction and the XGBoost model for intrusion detection. By customizing the reptile search algorithm...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/13/23/12687 |
_version_ | 1797400445439705088 |
---|---|
author | Mohamed Salb Luka Jovanovic Nebojsa Bacanin Milos Antonijevic Miodrag Zivkovic Nebojsa Budimirovic Laith Abualigah |
author_facet | Mohamed Salb Luka Jovanovic Nebojsa Bacanin Milos Antonijevic Miodrag Zivkovic Nebojsa Budimirovic Laith Abualigah |
author_sort | Mohamed Salb |
collection | DOAJ |
description | This paper addresses the critical security challenges in the internet of things (IoT) landscape by implementing an innovative solution that combines convolutional neural networks (CNNs) for feature extraction and the XGBoost model for intrusion detection. By customizing the reptile search algorithm for hyperparameter optimization, the methodology provides a resilient defense against emerging threats in IoT security. By applying the introduced algorithm to hyperparameter optimization, better-performing models are constructed capable of efficiently handling intrusion detection. Two experiments are carried out to evaluate the introduced technique. The first experiment tackles detection through binary classification. The second experiment handles the task by specifically identifying the type of intrusion through multi-class classification. A publicly accessible real-world dataset has been utilized for experimentation and several contemporary algorithms have been subjected to a comparative analysis. The introduced algorithm constructed models with the best performance in both cases. The outcomes have been meticulously statistically evaluated and the best-performing model has been analyzed using Shapley additive explanations to determine feature importance for model decisions. |
first_indexed | 2024-03-09T01:55:35Z |
format | Article |
id | doaj.art-45ad6a04dfba4915aedd503711c4588b |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T01:55:35Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-45ad6a04dfba4915aedd503711c4588b2023-12-08T15:11:25ZengMDPI AGApplied Sciences2076-34172023-11-0113231268710.3390/app132312687Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search AlgorithmMohamed Salb0Luka Jovanovic1Nebojsa Bacanin2Milos Antonijevic3Miodrag Zivkovic4Nebojsa Budimirovic5Laith Abualigah6Department of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, SerbiaDepartment of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, SerbiaDepartment of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, SerbiaDepartment of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, SerbiaDepartment of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, SerbiaDepartment of Informatics and Computing, Singidunum University, Danijelova 32, 11000 Belgrade, SerbiaComputer Science Department, Al al-Bayt University, Mafraq 25113, JordanThis paper addresses the critical security challenges in the internet of things (IoT) landscape by implementing an innovative solution that combines convolutional neural networks (CNNs) for feature extraction and the XGBoost model for intrusion detection. By customizing the reptile search algorithm for hyperparameter optimization, the methodology provides a resilient defense against emerging threats in IoT security. By applying the introduced algorithm to hyperparameter optimization, better-performing models are constructed capable of efficiently handling intrusion detection. Two experiments are carried out to evaluate the introduced technique. The first experiment tackles detection through binary classification. The second experiment handles the task by specifically identifying the type of intrusion through multi-class classification. A publicly accessible real-world dataset has been utilized for experimentation and several contemporary algorithms have been subjected to a comparative analysis. The introduced algorithm constructed models with the best performance in both cases. The outcomes have been meticulously statistically evaluated and the best-performing model has been analyzed using Shapley additive explanations to determine feature importance for model decisions.https://www.mdpi.com/2076-3417/13/23/12687internet of thingsfeature reductionconvolutional neural networksXGBoostreptile search algorithm |
spellingShingle | Mohamed Salb Luka Jovanovic Nebojsa Bacanin Milos Antonijevic Miodrag Zivkovic Nebojsa Budimirovic Laith Abualigah Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm Applied Sciences internet of things feature reduction convolutional neural networks XGBoost reptile search algorithm |
title | Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm |
title_full | Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm |
title_fullStr | Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm |
title_full_unstemmed | Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm |
title_short | Enhancing Internet of Things Network Security Using Hybrid CNN and XGBoost Model Tuned via Modified Reptile Search Algorithm |
title_sort | enhancing internet of things network security using hybrid cnn and xgboost model tuned via modified reptile search algorithm |
topic | internet of things feature reduction convolutional neural networks XGBoost reptile search algorithm |
url | https://www.mdpi.com/2076-3417/13/23/12687 |
work_keys_str_mv | AT mohamedsalb enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm AT lukajovanovic enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm AT nebojsabacanin enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm AT milosantonijevic enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm AT miodragzivkovic enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm AT nebojsabudimirovic enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm AT laithabualigah enhancinginternetofthingsnetworksecurityusinghybridcnnandxgboostmodeltunedviamodifiedreptilesearchalgorithm |