A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT)
The Internet of Things (IoT) has emerged as a new technological world connecting billions of devices. Despite providing several benefits, the heterogeneous nature and the extensive connectivity of the devices make it a target of different cyberattacks that result in data breach and financial loss. T...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/14/4884 |
id |
doaj-e69402e364f3409f9436bc6ef8e7a401 |
---|---|
record_format |
Article |
spelling |
doaj-e69402e364f3409f9436bc6ef8e7a4012021-07-23T14:06:06ZengMDPI AGSensors1424-82202021-07-01214884488410.3390/s21144884A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT)Danish Javeed0Tianhan Gao1Muhammad Taimoor Khan2Ijaz Ahmad3Software College, Northeastern University, Shenyang 110169, ChinaSoftware College, Northeastern University, Shenyang 110169, ChinaRiphah Institute of Science and Engineering, Islamabad 44000, PakistanShenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518000, ChinaThe Internet of Things (IoT) has emerged as a new technological world connecting billions of devices. Despite providing several benefits, the heterogeneous nature and the extensive connectivity of the devices make it a target of different cyberattacks that result in data breach and financial loss. There is a severe need to secure the IoT environment from such attacks. In this paper, an SDN-enabled deep-learning-driven framework is proposed for threats detection in an IoT environment. The state-of-the-art Cuda-deep neural network, gated recurrent unit (Cu- DNNGRU), and Cuda-bidirectional long short-term memory (Cu-BLSTM) classifiers are adopted for effective threat detection. We have performed 10 folds cross-validation to show the unbiasedness of results. The up-to-date publicly available CICIDS2018 data set is introduced to train our hybrid model. The achieved accuracy of the proposed scheme is 99.87%, with a recall of 99.96%. Furthermore, we compare the proposed hybrid model with Cuda-Gated Recurrent Unit, Long short term memory (Cu-GRULSTM) and Cuda-Deep Neural Network, Long short term memory (Cu- DNNLSTM), as well as with existing benchmark classifiers. Our proposed mechanism achieves impressive results in terms of accuracy, F1-score, precision, speed efficiency, and other evaluation metrics.https://www.mdpi.com/1424-8220/21/14/4884Internet of Things (IoT)intrusion detectiondeep learning (DL)software-defined network (SDN) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Danish Javeed Tianhan Gao Muhammad Taimoor Khan Ijaz Ahmad |
spellingShingle |
Danish Javeed Tianhan Gao Muhammad Taimoor Khan Ijaz Ahmad A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT) Sensors Internet of Things (IoT) intrusion detection deep learning (DL) software-defined network (SDN) |
author_facet |
Danish Javeed Tianhan Gao Muhammad Taimoor Khan Ijaz Ahmad |
author_sort |
Danish Javeed |
title |
A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT) |
title_short |
A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT) |
title_full |
A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT) |
title_fullStr |
A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT) |
title_full_unstemmed |
A Hybrid Deep Learning-Driven SDN Enabled Mechanism for Secure Communication in Internet of Things (IoT) |
title_sort |
hybrid deep learning-driven sdn enabled mechanism for secure communication in internet of things (iot) |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-07-01 |
description |
The Internet of Things (IoT) has emerged as a new technological world connecting billions of devices. Despite providing several benefits, the heterogeneous nature and the extensive connectivity of the devices make it a target of different cyberattacks that result in data breach and financial loss. There is a severe need to secure the IoT environment from such attacks. In this paper, an SDN-enabled deep-learning-driven framework is proposed for threats detection in an IoT environment. The state-of-the-art Cuda-deep neural network, gated recurrent unit (Cu- DNNGRU), and Cuda-bidirectional long short-term memory (Cu-BLSTM) classifiers are adopted for effective threat detection. We have performed 10 folds cross-validation to show the unbiasedness of results. The up-to-date publicly available CICIDS2018 data set is introduced to train our hybrid model. The achieved accuracy of the proposed scheme is 99.87%, with a recall of 99.96%. Furthermore, we compare the proposed hybrid model with Cuda-Gated Recurrent Unit, Long short term memory (Cu-GRULSTM) and Cuda-Deep Neural Network, Long short term memory (Cu- DNNLSTM), as well as with existing benchmark classifiers. Our proposed mechanism achieves impressive results in terms of accuracy, F1-score, precision, speed efficiency, and other evaluation metrics. |
topic |
Internet of Things (IoT) intrusion detection deep learning (DL) software-defined network (SDN) |
url |
https://www.mdpi.com/1424-8220/21/14/4884 |
work_keys_str_mv |
AT danishjaveed ahybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT tianhangao ahybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT muhammadtaimoorkhan ahybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT ijazahmad ahybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT danishjaveed hybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT tianhangao hybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT muhammadtaimoorkhan hybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot AT ijazahmad hybriddeeplearningdrivensdnenabledmechanismforsecurecommunicationininternetofthingsiot |
_version_ |
1721285925049204736 |