Strengthening IOT Security by Using Ensemble Learning and Feature Selection for Intelligent Intrusion Detection Based on Complete UNSW-NB15 And Iotid20 Datasets

Pritimayee Satapathy; Prafulla Kumar Behera

Author(s)

Pritimayee Satapathy Department of Computer Science and Applications, Utkal University,Vani Vihar, Bhubaneswar 751004, Odisha,India

Prafulla Kumar Behera Department of Computer Science and Applications, Utkal University,Vani Vihar, Bhubaneswar 751004, Odisha,India

Abstract

Internet of Things (IoT) refers to a collection of devices with sensors or actuators, capable of sending and receiving data that are linked together over wireless networks. As the number of internet-connected gadgets is growing at a brisk pace, a huge volume of data is being passed through these devices. This calls for the development and optimization of algorithms related to network security such as Intrusion Detection Systems (IDSs) to keep data secure during transmission. As a result, IDSs are frequently used along with additional safety solutions like firewalls and access control for data security. Various Machine Learning (ML) based strategies have been used for customizing IDSs to meet the ever-increasing demands of secured networks based on a subset of IoT Intrusion detection dataset. In the present study, we implemented an ensemble ML technique applied to the full version of IoT Intrusion Dataset 2020 (IoTID20) as well as UNSW-NB15 datasets to carry out multiple experiments. ML methods including, Logistic Regression (LR), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) have been used to build the primary classifier and the meta-classifier respectively in the proposed model. ML-based IDSs often encounter challenges such as a rise in the false positive rate, reduced detection accuracy, and prolonged model-building time when training is conducted on several imbalanced datasets. We implemented a random forest classifier's feature importance score to evaluate all of the pre-processed data and generate a shortened feature set, which simplifies the process of creating models and increases detection accuracy. The evaluation assessment shows that the recommended approach exhibits superior performance when compared to the models published in the literature, achieving 99.14% detection accuracy on UNSW-NB15 datasets with only 12 out of 47 network features and 99.94% detection accuracy on IoTID20 datasets with only 16 out of 83 network features

Publication Details

Page(s) 42-70

DOI DOI not available

Published Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: S1, Year: 2024

Request the full text from PASTIC

Keywords

machine learning, Internet of Things, network security, Anomaly Detection, Cybersecurity, IoTID20, feature engineering UNSW-NB15, intrusion detection system.

References

Ahanger TA,Aljumah A,Atiquzzaman M .2022 .State-of-the-art survey of artificial intelligent techniques for IoT security. Computer Networks, 108771 : .

Sensors .2022 .. , 22(10) : 3744.

Ullah S,Ahmad J,Khan MA,Alkhammash EH,Hadjouni M,Ghadi YY .2022 .A new intrusion detection system for the internet of things via deep convolutional neural network and feature engineering. Sensors, 22(10) : 3607.

Moustafa N,Slay J .2015 .a comprehensive data set for network intrusion detection systems (UNSW-NB15 network data set. 2015 military communications and information systems conference (MilCIS), : .

Kumar S,Gupta S,Arora S. .2021 .Research trends in network -based intrusion detection systems: A review. IEEE Access, 9 : 157761-79.

Tsimenidis S,Lagkas T,Rantos K. .2022 .Deep learning in IoT intrusion detection. Journal of network and systems management, 30 : 1-40.

.2017 .. 2017 International Conference on New Trends in Computing Sciences (ICTCS), : .

Agarwal A,Sharma P,Alshehri M,Mohamed AA,Alfarraj O .2021 .Classification model for accuracy and intrusion detection using machine learning approach. PeerJ Computer Science, 7 : e437.

Kasongo SM,Sun Y .2020 .Performance analysis of intrusion detection systems using a feature selection method on the UNSW-NB15 dataset. Journal of Big Data, 7 : 1-20.

Moustafa N,Slay J. .2016 .The evaluation of Network Anomaly Detection Systems: Statistical analysis of the UNSW-NB15 data set and the comparison with the KDD99 data set. Information Security Journal: A Global Perspective, 25(1-3) : 18-31.

Thockchom N,Singh MM,Nandi U. .2023 .A novel ensemble learning-based model for network intrusion detection. Complex & Intelligent Systems, : 1-22.

Rajagopal S,Kundapur PP,Hareesha KS PP .2020 .A stacking ensemble for network intrusion detection using heterogeneous datasets. Security and Communication Networks, : 1-9.

Moustafa N,Slay J. .2017 .A hybrid feature selection for network intrusion detection systems: Central points. arXiv preprint arXiv:170705505, : .

Thakkar A,Lohiya R .2023 .Fusion of statistical importance for feature selection in Deep Neural Network-based Intrusion Detection System. Information Fusion, 90 : 353-63.

Vinayakumar R,Alazab M,Soman K,Poornachandran P,Al-Nemrat A,Venkatraman S. .2019 .Deep learning approach for intelligent intrusion detection system. Ieee Access, 7 : 41525-50.

hew YJ,Lee N,Ooi SY,Wong K-S .2022 .Benchmarking full version of GureKDDCup, UNSW-NB15, and CIDDS-001 NIDS datasets using rolling-origin resampling. Information Security Journal: A Global Perspective, 31(5) : 544-65.

Albulayhi K,Abu Al-Haija Q,Alsuhibany SA,Jillepalli AA,Ashrafuzzaman M,Sheldon FT .2022 .IoT intrusion detection using machine learning with a novel high performing feature selection method. Applied Sciences, 12(10) : 5015.

Song Y,Hyun S,Cheong Y-G. .2021 .Analysis of autoencoders for network intrusion detection. Sensors, 21(13) : 4294.

Islam N,Farhin F,Sultana I,Kaiser MS,Rahman MS,Mahmud M .2021 .. Towards Machine Learning Based Intrusion Detection in IoT Networks. Computers, Materials & Continua, 69(2) : .

Qaddoura R,Al-Zoubi AM,Almomani I,Faris H I .2021 .A multi-stage classification approach for iot intrusion detection based on clustering with oversampling. Applied Sciences, 11(7) : 3022.

Prusa J,Khoshgoftaar TM,Seliya N .2015 .. 2015 IEEE 14th International Conference on Machine Learning and Applications, : .

Pedregosa F,Varoquaux G,Gramfort A,Michel V,Thirion B,Grisel O .2011 .. Scikitlearn: Machine learning in Python. the Journal of machine Learning research, 12 : 2825-30.

Kang H,Ahn DH,Lee GM,Yoo J,Park KH,Kim HK .2019 .IoT network intrusion dataset. IEEE Dataport, 10 : q70p-q449.

Ullah I,Mahmoud QH .2020 .A scheme for generating a dataset for anomalous activity detection in iot networks. Canadian AI, 13 : .

Dahouda MK,Joe I. .2021 .A deep-learned embedding technique for categorical features encoding. IEEE Access, 9 : 114381-91.

Chen R-C,Dewi C,Huang S-W .2020 .Selecting critical features for data classification based on machine learning methods. Journal of Big Data, 7(1) : 52.

Saheed YK,Abiodun AI,Misra S,Holone MK,Colomo-Palacios R. .2022 .A machine learningbased intrusion detection for detecting internet of things network attacks. Alexandria Engineering Journal, 61(12) : 9395-409.

Dhaliwal SS,Nahid A-A,Abbas R .2018 .Effective intrusion detection system using XGBoost. Information, 9(7) : 149.

Chen T,Guestrin C .2016 .A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining;, : .

Janarthanan T,Zargari S .2017 .. Feature selection in UNSW-NB15 and KDDCUP'99 datasets. 2017 IEEE 26th international symposium on industrial electronics (ISIE), : .

Moustafa N,Creech G,Slay J .2017 .Anomaly detection system using beta mixture models and outlier detection. Progress in Computing, Analytics and Networking: Proceedings of ICCAN, : .

Anwer HM,Farouk M,Abdel-Hamid A .2018 .A framework for efficient network anomaly intrusion detection with features selection. 2018 9th International Conference on Information and Communication Systems (ICICS), : .

Krishnan S,Neyaz A,Liu Q. .2021 .IoT network attack detection using supervised machine learning. , : .