Detection of Bruteforce attacks on the MQTT protocol using random forest algorithm

Akbar, Galuh Muhammad Iman, Hariyadi, Mokhamad Amin ORCID: https://orcid.org/0000-0001-9327-7604 and Hanani, Ajib ORCID: https://orcid.org/0000-0003-3557-4488 (2023) Detection of Bruteforce attacks on the MQTT protocol using random forest algorithm. Internet of Things and Artificial Intelligence Journal, 3 (3). pp. 250-272. ISSN 2774-4353

Text 24638.pdf - Published Version Available under License Creative Commons Attribution Share Alike. Download (1MB)

Abstract

Bruteforce is a hacking technique that launches an attack by guessing the username and password of the system that is the target of the attack. The Bruteforce attack on the MQTT protocol is an attack that often occurs on the IoT, so it is necessary to detect attacks on the MQTT protocol to find out normal traffic and brute force traffic. Random Forest was chosen because this method can classify a lot of data in a relatively short time, and the results from Random Forest can improve accuracy and prevent overfitting in the data classification process. This study uses two types of data: primary data from the hacking environment lab and secondary data from the IEEE Data Port MQTT-IOT-IDS2020 dataset. Trials on primary data and the results obtained are accuracy of 99.55%, precision of 100%, recall of 99.54%, and f-measure of 99.77%, the duration needed to get these results with 1796 data lines, i.e., for 0 seconds. As for the secondary data, the researcher obtained an accuracy of 99.77%, a precision of 100%, a recall of 99.43%, and an f-measure of 98.71%, the duration required to obtain these results with 85002 data lines, i.e., for 62 seconds.

Item Type:	Journal Article
Keywords:	Bruteforce; Random Forest; IoT Attack Detection; Protocol MQTT
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0899 Other Information and Computing Sciences > 089999 Information and Computing Sciences not elsewhere classified
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Ajib Hanani
Date Deposited:	28 Oct 2025 09:43

Downloads

Origin of downloads

Actions (login required)

View Item