Improving IoT Security with Balanced Resampling and Deep Learning

Yassine El Yamani; Youssef Baddi; Najib El Kamoun; Mehdia Ajana El Khaddar

Author(s)

Yassine El Yamani Mr., STIC Lab, FSJ, Chouaib Doukkali University, El Jadida, Morocco

Youssef Baddi Dr., STIC Lab, FSJ, Chouaib Doukkali University, El Jadida, Morocco

Najib El Kamoun Dr., STIC Lab, FSJ, Chouaib Doukkali University, El Jadida, Morocco

Mehdia Ajana El Khaddar Ms., Engineering Science Lab, ENSA, Ibn Tofail University, Kenitra, Morocco

Abstract

The rapid growth of the Internet of Things (IoT) has created an urgent need for robust security measures against advanced cyber threats. This research introduces a novel approach to detecting attacks on IoT devices by combining balanced resampling with deep learning models like CNN, GRU, DNN, and CNN-LSTM. Unlike traditional methods, our strategy dynamically adjusts class distribution to ensure balanced representation of both majority and minority classes, thus improving detection accuracy. Using the N-BaIoT dataset, which includes data from various IoT devices under Mirai and BASHLITE botnet attacks, we rigorously evaluate our method on seven different devices. We show herein that our method, even when used with limited data, provides major improvements in precision, recall, F1score and loss metrics compared to other existing methods. Therefore, our study aims at providing an enhanced security model for IoT, which provides a better detection accuracy and reliability by effectively integrating deep learning models with data preprocessing.

Publication Details

Page(s) 1-15

DOI DOI not available

Published Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: 3, Year: 2024

Request the full text from PASTIC

Keywords

SMOTE, IoT, Resampling, N-BaIoT Dataset, Botnet Attack Detection

References

El Yamani Y.,Baddi Y.,Kamoun N. El,Jun J. Reliab. Intell. Environ. .2024 .A survey: Contribution of ML & DL to the detection & prevention of botnet attacks,”. , : .

Baddi and M. D. Cherif El Y.,Kettani Y.,Apr Y. .2022 .QoS-VNS-CS: QoS constraints Core Selection Algorithm based on variable neighborhood search algorithm,” IJCNIS. , 6(1) : 454.

Meidan Y. .2018 .“N-BaIoT-Network-Based Detection of IoT botnet attacks using deep autoencoders,” IEEE Pervasive Comput. , 03367731(3) : 12-22.

Alkahtani H.,Aldhyani T. H. H. .2021 .Botnet attack detection by using CNN-LSTM model for Internet of Things applications. , : 1-23.

Popoola S. I.,Adebisi B.,Ande R.,Hammoudeh M.,Anoh K.,Atayero A. A.,Apr A. A. .2021 .SMOTE-DRNN: A deep learning algorithm for botnet detection in the Internet-of-Things networks. , 21(9) : 2985.

Bagui S. S.,Mink D.,Bagui S. C.,Subramaniam S.,Oct S. .2023 .Determining resampling ratios using BSMOTE and SVM-SMOTE for identifying rare attacks in imbalanced cybersecurity data,” Comput.. , 12(10) : 204.

Qazi E. U. H.,Almorjan A.,Aug A. .2022 .A One-Dimensional Convolutional Neural Network (1D-CNN) based deep learning system for network intrusion detection. ” Appl. Sci., 12(16) : 7986.

Hasan T.,Akhunzada A.,Giannetsos T.,Malik J. .2020 .Network Softwarization (NetSoft). doi: 10.1109/netsoft48620, 9165424 : .

YAMANI EL .2024 .Hybrid models for iot security: Tackling class imbalance. In The 11th International Conference on Wireless Networks and Mobile Communications, : .

Antonakakis M. .2017 .“Understanding the mirai botnet. ” in 26th USENIX Security Symposium (USENIX Security 17), : 1093-1110.

Spring T.,infects- T.,- T. .2024 ./bashlite-family-of-malware-. , 12 : .

Tarawneh A. S.,Hassanat A. B. A.,Almohammadi K.,Chetverikov D.,Bellinger C. .2020 .Synthetic Minority Over-Sampling Technique based on furthest neighbour algorithm. ” IEEE Access, 2983003 : 59069-59082.

Rawat S. S.,Mishra A. K. .2022 .Review of methods for handling class-imbalanced in classification problems. , : .

Johnson J. M.,T. M. Khoshgoftaar J. M.,Mar J. M. .2019 .Survey on deep learning with class imbalance. ” J. Big Data, 6(1) : .

Tanha J.,Abdi Y.,Samadi N.,Razzaghi N.,Asadpour M.,Sep M. .2020 .Boosting methods for multi-class imbalanced data classification: an experimental review. ” J. Big Data, 7(1) : .

He H. .2013 .. , : .

Brownlee J. .2024 ./random-oversampling-and-undersampling-for-imbalancedclassification/ (accessed Jun. , 12 : .

Guo H.,Li Y.,Shang J.,Gu M.,Huang Y.,Gong B. .2016 .Learning from class-imbalanced data: Review of methods and applications. ” Expert Syst. Appl., 12 : 220-239.

Chawla N. V.,Bowyer K. W.,Hall L. O.,Kegelmeyer W. P.,Artif J. .2002 .Synthetic Minority Over-sampling Technique,”. Intell. Res., 16 : 321-357.

He H.,Garcia E. A. .2008 .Learning from imbalanced data,”. IEEE Trans. Knowl. Data Eng., 239(9) : 1263-1284.

Fernandez A.,Garcia S.,Herrera F.,Chawla N. V.,Artif J. .2018 .SMOTE for Learning from imbalanced data: Progress and challenges, marking the 15-year anniversary,”. Intell. Res., 61 : 863-905.

Batista G. E. A. P. A.,Prati R. C.,Monard M. C. .2004 .A study of the behavior of several methods for balancing machine learning training data,” ACM SIGKDD Explorations Newsl. , 6(1) : 20-29.

Luque A.,Carrasco A.,Martín A. .2019 .The impact of class imbalance in classification performance metrics based on the binary confusion matrix,” Pattern Recognit. , 02 : 216-231.

Davis J.,Goadrich M. .2006 .The relationship between Precision-Recall and ROC curves,”. in Pro. 23rd Int. Conf. Machine Learning-ICML'06, : 233-240.

Hossin M.,Sulaiman M. N. .2015 .A review on evaluation metrics for data classification evaluations. ” Int. J. Data Min. Knowl. Manage. Process, 5201(2) : 01-11.

Buja A.,Stuetzle W.,Shen Y. .2024 .Loss functions for binary class probability estimation and classification: Structure and applications. Accessed: Jun. 12, : .

Grandini M. .2008 .Metrics for multi-class classification: An overview. , 05756 : .