Scalable wi-fi intrusion detection for IoT systems

Örs, Faik Kerem and Aydın, Mustafa and Boğatarkan, Aysu and Levi, Albert (2021) Scalable wi-fi intrusion detection for IoT systems. In: 11th IFIP International Conference on New Technologies, Mobility and Security (NTMS), Paris, France

Full text not available from this repository. (Request a copy)

Abstract

The pervasive and resource-constrained nature of Internet of Things (IoT) devices makes them attractive to be targeted by different means of cyber threats. There are a vast amount of botnets being deployed every day that aim to increase their presence on the Internet for realizing malicious activities with the help of the compromised interconnected devices. Therefore, monitoring IoT networks using intrusion detection systems is one of the major countermeasures against such threats. In this work, we present a machine learning based Wi-Fi intrusion detection system developed specifically for IoT devices. We show that a single multi-class classifier, which operates on the encrypted data collected from the wireless data link layer, is able to detect the benign traffic and six types of IoT attacks with an overall accuracy of 96.85%. Our model is a scalable one since there is no need to train different classifiers for different IoT devices. We also present an alternative attack classifier that outperforms the attack classification model which has been developed in an existing study using the same dataset.
Item Type: Papers in Conference Proceedings
Uncontrolled Keywords: anomaly detection; attack classification; Internet of Things (IoT); intrusion detection; Wi-Fi security; wireless network security
Divisions: Faculty of Engineering and Natural Sciences
Depositing User: Albert Levi
Date Deposited: 02 Sep 2022 11:18
Last Modified: 02 Sep 2022 11:18
URI: https://research.sabanciuniv.edu/id/eprint/43494

Actions (login required)

View Item
View Item