Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks

Detecting intrusions in Internet of Things (IoT) networks is critical for maintaining cybersecurity. Traditional Intrusion Detection Systems (IDS) often face challenges in identifying unknown attacks and tend to have high false positive rates. To address these issues, we propose the Ensemble of Deep...

Full description

Saved in:
Bibliographic Details
Main Authors: Deepesh M. Dhanvijay, Mrinai M. Dhanvijay, Vaishali H. Kamble
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-12-01
Series:Cyber Security and Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772918425000050
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850031856394698752
author Deepesh M. Dhanvijay
Mrinai M. Dhanvijay
Vaishali H. Kamble
author_facet Deepesh M. Dhanvijay
Mrinai M. Dhanvijay
Vaishali H. Kamble
author_sort Deepesh M. Dhanvijay
collection DOAJ
description Detecting intrusions in Internet of Things (IoT) networks is critical for maintaining cybersecurity. Traditional Intrusion Detection Systems (IDS) often face challenges in identifying unknown attacks and tend to have high false positive rates. To address these issues, we propose the Ensemble of Deep Learning Models with Prediction Scoring-based Optimized Feature Sets (EDLM-PSOFS). Our approach begins with data preprocessing utilizing MissForest imputation and label one-hot encoding, effectively managing incomplete and categorical data.For feature selection, we employ the Median-based Shapiro-Wilk test alongside Correlation-Adaptive LASSO Regression (CALR) to ensure robust feature extraction. To capture temporal patterns effectively, our ensemble integrates Global Attention Long Short-Term Memory networks (GA-LSTMs), utilizing layered structures, residual connections, and attention mechanisms. Additionally, to enhance interpretability and support decision-making, we incorporate the Exploit Prediction Scoring System (EPSS), which evaluates prediction scores and provides detailed insights, thereby improving overall model performance. This comprehensive methodology aims to strengthen the detection capabilities of IDS in IoT environments, reducing false positives while effectively identifying unknown threats.
format Article
id doaj-art-a8ae2aa0b6b44580a1561a94aa018f9d
institution DOAJ
issn 2772-9184
language English
publishDate 2025-12-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Cyber Security and Applications
spelling doaj-art-a8ae2aa0b6b44580a1561a94aa018f9d2025-08-20T02:58:51ZengKeAi Communications Co., Ltd.Cyber Security and Applications2772-91842025-12-01310008810.1016/j.csa.2025.100088Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networksDeepesh M. Dhanvijay0Mrinai M. Dhanvijay1Vaishali H. Kamble2Department of Electronics and Communication Engineering, National Institute of Technology, Trichy, Tiruchirappalli, IndiaDepartment of Electronics and Telecommunication Engineering, M.E.S. College of Engineering, Pune, India; Corresponding author.DES Pune University, PuneDetecting intrusions in Internet of Things (IoT) networks is critical for maintaining cybersecurity. Traditional Intrusion Detection Systems (IDS) often face challenges in identifying unknown attacks and tend to have high false positive rates. To address these issues, we propose the Ensemble of Deep Learning Models with Prediction Scoring-based Optimized Feature Sets (EDLM-PSOFS). Our approach begins with data preprocessing utilizing MissForest imputation and label one-hot encoding, effectively managing incomplete and categorical data.For feature selection, we employ the Median-based Shapiro-Wilk test alongside Correlation-Adaptive LASSO Regression (CALR) to ensure robust feature extraction. To capture temporal patterns effectively, our ensemble integrates Global Attention Long Short-Term Memory networks (GA-LSTMs), utilizing layered structures, residual connections, and attention mechanisms. Additionally, to enhance interpretability and support decision-making, we incorporate the Exploit Prediction Scoring System (EPSS), which evaluates prediction scores and provides detailed insights, thereby improving overall model performance. This comprehensive methodology aims to strengthen the detection capabilities of IDS in IoT environments, reducing false positives while effectively identifying unknown threats.http://www.sciencedirect.com/science/article/pii/S2772918425000050Cyber-attackEnsembleEPSSIntrusion detection systemIoTLSTM
spellingShingle Deepesh M. Dhanvijay
Mrinai M. Dhanvijay
Vaishali H. Kamble
Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks
Cyber Security and Applications
Cyber-attack
Ensemble
EPSS
Intrusion detection system
IoT
LSTM
title Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks
title_full Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks
title_fullStr Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks
title_full_unstemmed Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks
title_short Cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for IOT networks
title_sort cyber intrusion detection using ensemble of deep learning with prediction scoring based optimized feature sets for iot networks
topic Cyber-attack
Ensemble
EPSS
Intrusion detection system
IoT
LSTM
url http://www.sciencedirect.com/science/article/pii/S2772918425000050
work_keys_str_mv AT deepeshmdhanvijay cyberintrusiondetectionusingensembleofdeeplearningwithpredictionscoringbasedoptimizedfeaturesetsforiotnetworks
AT mrinaimdhanvijay cyberintrusiondetectionusingensembleofdeeplearningwithpredictionscoringbasedoptimizedfeaturesetsforiotnetworks
AT vaishalihkamble cyberintrusiondetectionusingensembleofdeeplearningwithpredictionscoringbasedoptimizedfeaturesetsforiotnetworks