SavedAdd your journal

Journals / Journal of Naval Sciences and Engineering / 2022 / Cilt: 18 - Sayı: 2

MACHINE AND DEEP LEARNING-BASED INTRUSION DETECTION AND COMPARISON IN INTERNET OF THINGS

MAKİNE VE DERİN ÖĞRENME YÖNTEMLERİ İLE NESNELERİN İNTERNETİ İÇİN SALDIRI TESPİTİNİN KARŞILAŞTIRILMASI

Siham AMAROUCHE
Kerem KÜÇÜK
Pages
333–361
Publication Date
2022-11-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The experiment was evaluated with the open database UNSW-NB15.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In today’s technology world, intrusion detection is important topic for the Internet of Things (IoT) systems.
📊
Key Findings & Data:In this article, we propose new detecting technique to improve performance and increase accuracy in NIDS.
💡
Conclusion & Impact:The experiment was evaluated with the open database UNSW-NB15.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Derin Öğrenme · IoT Güvenliği · Makine Öğrenmesi

Abstract

In today’s technology world, intrusion detection is important topic for the Internet of Things (IoT) systems. With the growth of using tiny devices connected to wireless networks in IoT, the amount of data is growing rapidly. This data may be vulnerable to attacks so that IoT systems need to secure it for increasing the system’s confidentiality, availability, and reliability. The progress of detecting attacks using artificial intelligence (AI) autonomously has become a more convenient method in network intrusion detection systems (NIDS). In this article, we propose new detecting technique to improve performance and increase accuracy in NIDS. We present different machine learning (ML) and deep learning (DL) methods to detect the different type of attacks for IoT systems. We also provide the experiments to find out the best way to identify the anomaly in IoT system environment, take comparisons between different AI models. The experiment was evaluated with the open database UNSW-NB15.

Özet

Günümüz teknoloji dünyasında, nesnelerin interneti (IoT) sistemleri için izinsiz giriş tespiti önemli bir konudur. IoT'de kablosuz ağlara bağlı küçük cihazların kullanımının artmasıyla birlikte veri miktarı da hızla artıyor. Bu veriler saldırılara karşı savunmasız olabilir, bu nedenle IoT sistemlerinin sistemin gizliliğini, kullanılabilirliğini ve güvenilirliğini artırmak için bu verileri güvenceye alması gerekir. Yapay zekayı (AI) otonom olarak kullanarak saldırıları tespit etme ilerlemesi, ağ saldırı tespit sistemlerinde (NIDS) daha uygun bir yöntem haline geldi. Bu yazıda, NIDS'de performansı iyileştirmek ve doğruluğu artırmak için yeni tespit tekniği öneriyoruz. IoT sistemleri için farklı saldırı türlerini tespit etmek için farklı makine öğrenimi (ML) ve derin öğrenme (DL) yöntemleri sunuyoruz. Ayrıca, IoT sistem ortamındaki anomaliyi tanımlamanın en iyi yolunu bulmak için deneyler sunuyoruz, farklı AI modelleri arasında karşılaştırmalar yapıyoruz. Deney, açık veri tabanı UNSW-NB15 ile değerlendirilmiştir.

🔖

Cite This Article

AMAROUCHE, S., KÜÇÜK, K. (2022). MACHINE AND DEEP LEARNING-BASED INTRUSION DETECTION AND COMPARISON IN INTERNET OF THINGS. Journal of Naval Sciences and Engineering, Cilt: 18 - Sayı: 2, 333–361. https://ajindex.com/articles/860574

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (2)

  1. Referans1 Abiodun, O. I., Jantan, A., Omolara, A. E., Dada, K. V., Mohamed, N. A., & Arshad, H. (2018). State-of-the-art in artificial neural network applications: A survey. Heliyon, 4(11), 1-41. doi:10.1016/j.heliyon.2018.e00938 Referans2 Albawi, S., Mohammed, T.A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. In 2017 International Conference on Engineering and Technology (ICET) (pp. 1-6).
  2. Turkey, IEEE. doi:10.1109/ICEngTechnol.2017.8308186 Referans3 Alsamiri, J., & Alsubhi, K. (2019). Internet of Things cyber attacks detection using machine learning. International Journal of Advanced Computer Science and Applications, 10(12), 627-634.‏ doi:10.14569/ijacsa.2019.0101280 Referans4 Amidi, S., & Amidi, A. (2019). Recurrent Neural Networks Cheatsheet. Stanford Education. Retrieved August 19, 2021, from https://stanford.edu/~shervine/teaching/cs-230/cheatsheet-recurrent-neural-networks#overview Referans5 Boateng, E. Y., & Abaye, D. A. (2019). A review of the logistic regression model with emphasis on medical research. Journal of Data Analysis and Information Processing, 7(4), 190-207.‏ doi:10.4236/jdaip.2019.74012 Referans6 Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32. Referans7 Chandrashekar, G., & Sahin, F. (2014). A survey on feature selection methods. Computers & Electrical Engineering, 40(1), 16-28.‏ doi:10.1016/j.compeleceng.2013.11.024 Referans8 Chomboon, K., Chujai, P., Teerarassamee, P., Kerdprasop, K., & Kerdprasop, N. (2015). An empirical study of distance metrics for k-nearest neighbor algorithm. In Proceedings of the 3rd international conference on industrial application engineering (pp. 280-285).‏ Japan, The Institute of Industrial Applications Engineers. doi:10.12792/iciae2015.051 Referans9 Gated recurrent unit. (2021, December 29). In Wikipedia. Retrieved June 23, 2021, from https://en.wikipedia.org/wiki/Gated_recurrent_unit Referans10 Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780.‏ doi:10.1162/neco.1997.9.8.1735 Referans11 Jonathan, J. (n.d.). What’s a Deep Neural Network? Deep Nets Explained. BMC Software Blogs. Retrieved March 10, 2021, from https://www.bmc.com/blogs/deep-neural-network/ Referans12 Jozefowicz, R., Zaremba, W., & Sutskever, I. (2015, June). An empirical exploration of recurrent network architectures. In F. R. Bach & D. M. Blei (eds.), International conference on machine learning (pp. 2342-2350). PMLR.‏ Referans13 Kasongo, S.