Comparing Machine Learning and Deep Learning for IoT Botnet Detection

Botnets have become a major threat to Internet of Things (IoT) devices due to their low security settings out of the box and the lack of security awareness from end users. Many ports are open by default and default user credentials are left unchanged. To tackle the increasingly popular botnet attack...

Full description

Saved in:
Bibliographic Details
Main Authors: Gandhi, Rishabh, Li, Yanyan
Format: Conference Proceeding
Language:English
Subjects:
Botnet
Convolutional neural networks
DDoS Attack
Deep learning
Internet of Things
Machine Learning
Malware
Network Security
Performance evaluation
Random Forest
Security
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Botnets have become a major threat to Internet of Things (IoT) devices due to their low security settings out of the box and the lack of security awareness from end users. Many ports are open by default and default user credentials are left unchanged. To tackle the increasingly popular botnet attack, many detection approaches have been proposed. However, most of them are targeting on one particular approach or one botnet dataset. There is lacking a comprehensive comparison between different machine learning and deep learning approaches on this task under different datasets collected from different ways. In this work, we have measured the performance of 5 machine learning and 2 deep learning based approaches on 4 recently published IoT botnet datasets collected using real and virtual IoT devices under Mirai malware attack. Our comparison results have shown that random forest achieved the best detection accuracy as well as the shortest testing time.
ISSN:2693-8340
DOI:10.1109/SMARTCOMP52413.2021.00053