University of Twente Student Theses


Malware detection in IoT devices using Machine Learning

Dartel, Bram van (2021) Malware detection in IoT devices using Machine Learning.

[img] PDF
Abstract:The Internet of Things (IoT) is growing rapidly all over the world, while its security lacks behind. More than 30% of all the infections observed in mobile networks were targeted on IoT. Machine learning is suited for detecting malware on these, often unsupervised, devices and the results are promising. At this point, however, such detection in a single IoT node has not been done yet because IoT nodes often have weak processors. In this project, the possibilities of malware detection in a single IoT device are investigated by trying to scale machine learning algorithms such that a single IoT device can perform near real-time network traffic anomaly detection, marking packets as ‘malware’ or ‘benign’. Using one of the machine learning algorithms, it is possible to implement the proposed program on an ESP32-chip that can classify data points from the IoT-23 dataset. When fully implemented, this could mean that, in the future, IoT devices will be able to check for themselves whether a network connection is part of a malware attack or if it is a ‘normal’ connection.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page