Novel Machine Learning (ML) Algorithms to Classify IPv6 Network Traffic in Resource-Limited Systems

---

Yılmaz Y., Buyrukoğlu S., Alım M.

Computer Science, cilt.2022, sa.1, ss.219-224, 2022 (Hakemli Dergi)

• Yayın Türü: Makale / Tam Makale
• Cilt numarası: 2022 Sayı: 1
• Basım Tarihi: 2022
• Doi Numarası: 10.53070/bbd.1172706
• Dergi Adı: Computer Science
• Sayfa Sayıları: ss.219-224
• Açık Arşiv Koleksiyonu: AVESİS Açık Erişim Koleksiyonu
• Recep Tayyip Erdoğan Üniversitesi Adresli: Evet

Özet

Abstract— Providing machine learning (ML) based security in heterogeneous IoT networks includingresource-constrained devices is a challenge because of the fact that conventional ML algorithms requireheavy computations. Therefore, in this paper, lightweight ProtoNN, CMSIS-NN, and Bonsai tree MLalgorithms were evaluated by using performance metrics such as testing accuracy, precision, F1 scoreand recall to test their classification ability on the IPv6 network dataset generated on resource-scarceembedded devices. The Bonsai tree algorithm provided the best performance results in all metrics (98.8in accuracy, 98.9% in F1 score, 99.2% in precision, and 98.8% in recall) compared to the ProtoNN, andCMSIS-NN algorithms.Keywords : Embedded systems, machine learning, lightweight ML algorithms, IPv6 Network, cyberattack