PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things

Network Intrusion Detection Systems (NIDS) play a crucial role in IoT security. In recent years, deep learning-based intrusion detection systems have demonstrated excellent performance. However, the high computational and storage requirements make these impractical for most IoT devices. To address t...

Full description

Saved in:
Bibliographic Details
Main Authors: Auwal Sani Iliyasu, Abdul Jabbar Siddiqui, Houbing Song, Fahad Jibrin Abdu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11020677/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850218971355152384
author Auwal Sani Iliyasu
Abdul Jabbar Siddiqui
Houbing Song
Fahad Jibrin Abdu
author_facet Auwal Sani Iliyasu
Abdul Jabbar Siddiqui
Houbing Song
Fahad Jibrin Abdu
author_sort Auwal Sani Iliyasu
collection DOAJ
description Network Intrusion Detection Systems (NIDS) play a crucial role in IoT security. In recent years, deep learning-based intrusion detection systems have demonstrated excellent performance. However, the high computational and storage requirements make these impractical for most IoT devices. To address this pressing issue, we propose PNet-IDS, a novel lightweight convolutional neural network (CNN)-based method to reduce computational complexity and optimize on-device resource usage for real-time intrusion detection. The key contribution of the proposed method is the reduced number of floating point operations (FLOPs) and effective utilization of on-device computational resources at high accuracies and precision, making PNet-IDS lightweight and efficient for real-time next generation IoT intrusion detection. Moreover, PNet-IDS’ robustness against distribution shifts in network traffic is enhanced by through a knowledge distillation framework. Comprehensive experimental evaluations using the popular BoT-IoT and CIC-IDS2017 benchmark datasets prove the superiority of the proposed PNet-IDS over competitive related methods in terms of reduced parameters count, reduced FLOPs, reduced model size while maintaining high accuracy and precision. By combining PNet-IDS’ efficiency with knowledge distillation’s adaptability, the proposed method offers a scalable and resilient solution for IoT intrusion detection.
format Article
id doaj-art-cf74d64e90174a878aa9a698a478aaee
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-cf74d64e90174a878aa9a698a478aaee2025-08-20T02:07:31ZengIEEEIEEE Access2169-35362025-01-011310262410263910.1109/ACCESS.2025.357570511020677PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of ThingsAuwal Sani Iliyasu0Abdul Jabbar Siddiqui1https://orcid.org/0000-0001-6233-598XHoubing Song2https://orcid.org/0000-0003-2631-9223Fahad Jibrin Abdu3https://orcid.org/0000-0002-4942-1258Interdisciplinary Research Center for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi ArabiaInterdisciplinary Research Center for Intelligent Secure Systems, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi ArabiaDepartment of Information Systems, University of Maryland, Baltimore County, Baltimore, MD, USASDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum and Minerals (KFUPM), Dhahran, Saudi ArabiaNetwork Intrusion Detection Systems (NIDS) play a crucial role in IoT security. In recent years, deep learning-based intrusion detection systems have demonstrated excellent performance. However, the high computational and storage requirements make these impractical for most IoT devices. To address this pressing issue, we propose PNet-IDS, a novel lightweight convolutional neural network (CNN)-based method to reduce computational complexity and optimize on-device resource usage for real-time intrusion detection. The key contribution of the proposed method is the reduced number of floating point operations (FLOPs) and effective utilization of on-device computational resources at high accuracies and precision, making PNet-IDS lightweight and efficient for real-time next generation IoT intrusion detection. Moreover, PNet-IDS’ robustness against distribution shifts in network traffic is enhanced by through a knowledge distillation framework. Comprehensive experimental evaluations using the popular BoT-IoT and CIC-IDS2017 benchmark datasets prove the superiority of the proposed PNet-IDS over competitive related methods in terms of reduced parameters count, reduced FLOPs, reduced model size while maintaining high accuracy and precision. By combining PNet-IDS’ efficiency with knowledge distillation’s adaptability, the proposed method offers a scalable and resilient solution for IoT intrusion detection.https://ieeexplore.ieee.org/document/11020677/Deep learningconvolutional neural network (CNN)Internet of Things (IoT)knowledge distillation (KD)lightweight modelsnetwork intrusion detection system (NIDS)
spellingShingle Auwal Sani Iliyasu
Abdul Jabbar Siddiqui
Houbing Song
Fahad Jibrin Abdu
PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things
IEEE Access
Deep learning
convolutional neural network (CNN)
Internet of Things (IoT)
knowledge distillation (KD)
lightweight models
network intrusion detection system (NIDS)
title PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things
title_full PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things
title_fullStr PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things
title_full_unstemmed PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things
title_short PNet-IDS: A Lightweight and Generalizable Convolutional Neural Network for Intrusion Detection in Internet of Things
title_sort pnet ids a lightweight and generalizable convolutional neural network for intrusion detection in internet of things
topic Deep learning
convolutional neural network (CNN)
Internet of Things (IoT)
knowledge distillation (KD)
lightweight models
network intrusion detection system (NIDS)
url https://ieeexplore.ieee.org/document/11020677/
work_keys_str_mv AT auwalsaniiliyasu pnetidsalightweightandgeneralizableconvolutionalneuralnetworkforintrusiondetectionininternetofthings
AT abduljabbarsiddiqui pnetidsalightweightandgeneralizableconvolutionalneuralnetworkforintrusiondetectionininternetofthings
AT houbingsong pnetidsalightweightandgeneralizableconvolutionalneuralnetworkforintrusiondetectionininternetofthings
AT fahadjibrinabdu pnetidsalightweightandgeneralizableconvolutionalneuralnetworkforintrusiondetectionininternetofthings