Presentation information


International Session

International Session (Work in progress) » EW-2 Machine learning

[3N3-IS-2e] Machine learning (5/5)

Thu. Jun 10, 2021 3:20 PM - 5:00 PM Room N (IS room)

Chair: Hisashi Kashima (Kyoto University)

3:20 PM - 3:40 PM

[3N3-IS-2e-01] Anomaly Detection of IoT Cyber Attacks in Smart City Using Machine Learning

〇Ginta Hara1, Ahmed Moustafa1 (1. Nagoya Institute of Technology)


In this research, we aim to propose a new system of Networked Intrusion Detection System (NIDS) using machine learning, which aims to prevent known or unknown attacks by monitoring network traffic, taking into account the resource limitations of IoT devices.
The random forest used in previous studies cannot learn to take into account the time series of network traffic. Therefore, in this study, we propose a time-series-aware machine learning method using CNNs, which can learn from multiple network traffic as input.
In our experiments, we tried to detect anomalies in traffic by using 10 network traffic as input to the CNN.
As a result, we were able to show that our method can detect anomalies in network traffic with higher accuracy than the random forest method used in previous studies.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.