The Internet of things (IoT) has increased rapidly which led to a huge number of IOT cyberattacks. Malicious operations, MITM, DoS/DDoS, scan, and Botnet attacks are the primary attacks that can affect IoT devices security. Therefore, an accurate and efficient system that identifies malicious attacks and helps in reducing security risks associated to IoT devices has become mandatory. Network intrusion detection system has been generally admitted as an efficient and effective approach for dealing with network security threats. Also, to address increasingly sophisticated cyber security threats, machine learning methods in established IDS are used through an efficient and effective detection process. In this work, various machine learning classifiers, including K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Gaussian Naïve Bays (NB), XGBoost (XGB), Logistic Regression (LR), and Artificial Neural Networks: Multilayer Perceptron (MLP) is used to identify various categories of network attacks on IoT devices and to determine the best algorithm that leads to a good performance in detecting patterns of suspect IoT network activities. The IoT Botnet dataset has assessed such models using different performance measures such as precision, accuracy, recall, and F1-score. As a result, we observe that the studied models reached the best accuracy about 99.60% by implementing the MLP algorithm for multiclass traffic detection. Moreover, it shows a good performance concerning training time and prediction execution time, less than 307 ms.
Skip Nav Destination
Article navigation
11 July 2023
INTERNATIONAL CONFERENCE ON ADVANCES IN COMMUNICATION TECHNOLOGY AND COMPUTER ENGINEERING
24–25 June 2022
Meknes, Morocco
Research Article|
July 11 2023
A machine learning based intrusions detection for IoT botnet attacks
Yahya Rbah;
Yahya Rbah
a)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
a)Corresponding author: [email protected]
Search for other works by this author on:
Mohammed Mahfoudi;
Mohammed Mahfoudi
b)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
Search for other works by this author on:
Younes Balboul;
Younes Balboul
c)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
Search for other works by this author on:
Kaouthar Chetioui;
Kaouthar Chetioui
d)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
Search for other works by this author on:
Mohammed Fattah;
Mohammed Fattah
e)
2
Image Laboratory, University of Moulay Ismail
, Meknes, Morocco
Search for other works by this author on:
Said Mazer;
Said Mazer
f)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
Search for other works by this author on:
Moulhime Elbekkali;
Moulhime Elbekkali
g)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
Search for other works by this author on:
Benaissa Bernoussi
Benaissa Bernoussi
h)
1
Artificial Intelligence & Data Science & Emerging Systems Laboratory, Sidi Mohamed Ben Abdellah University
, Fez, Morocco
Search for other works by this author on:
AIP Conf. Proc. 2814, 030012 (2023)
Citation
Yahya Rbah, Mohammed Mahfoudi, Younes Balboul, Kaouthar Chetioui, Mohammed Fattah, Said Mazer, Moulhime Elbekkali, Benaissa Bernoussi; A machine learning based intrusions detection for IoT botnet attacks. AIP Conf. Proc. 11 July 2023; 2814 (1): 030012. https://doi.org/10.1063/5.0149102
Download citation file:
Pay-Per-View Access
$40.00
Sign In
You could not be signed in. Please check your credentials and make sure you have an active account and try again.
Citing articles via
Inkjet- and flextrail-printing of silicon polymer-based inks for local passivating contacts
Zohreh Kiaee, Andreas Lösel, et al.
Design of a 100 MW solar power plant on wetland in Bangladesh
Apu Kowsar, Sumon Chandra Debnath, et al.
Production and characterization of corncob biochar for agricultural use
Praphatsorn Rattanaphaiboon, Nigran Homdoung, et al.
Related Content
Implementing machine learning in cyber security-based IoT for botnets security detection by applying recurrent variational autoencoder
AIP Conf. Proc. (September 2024)
Botnet detection in internet of things (IOT) by swarm intelligence (SI) algorithm
AIP Conf. Proc. (November 2023)
Distributed denial of service (DDOS) in Internet of Things (IoT) environment: Classification and overview
AIP Conf. Proc. (July 2024)
A unified predictability for bot attack on IoT devices and its platforms
AIP Conference Proceedings (April 2022)
A detection of IoT based IDS attacks using deep neural network
AIP Conference Proceedings (July 2021)