A Dimensionality Reduction Approach for Machine Learning Based IoT Botnet Detection (Similarity)

Stiawan, Deris (2022) A Dimensionality Reduction Approach for Machine Learning Based IoT Botnet Detection (Similarity). Ithenticate Universitas sriwijaya. (Submitted)

[thumbnail of A_Dimensionality_Reduction_Approach_for_Machine_IE.pdf]
Preview
Text
A_Dimensionality_Reduction_Approach_for_Machine_IE.pdf

Download (1MB) | Preview

Abstract

The use of Internet of Thing (IoT) technology in industry or daily lives are improving massively. This improvement attracts hackers to perform cyber attack which one of them is botnet. One of the botnet threat is disrupting network and denial service to IoT devices. Therefore, a reliable detection system to keep the security is required urgently. One of the detection method which has been widely used by previous research works is machine learning. However, performance problem on machine learning needs more attention, especially for data with high scalability. In this paper, we conduct experiments on random projection dimensionality reduction approach to boost the machine learning performance to detect botnet IoT. Experiment results show random projection method combined with decision tree is able to detect IoT botnet within 8.44 seconds with accuracy of 100% and very low false positive rate (close to 0).

Item Type: Other
Subjects: T Technology > T Technology (General) > T58.6-58.62 Management information systems > T58.62 Decision support systems Cf. HD30.213 Industrial management
#3 Repository of Lecturer Academic Credit Systems (TPAK) > Results of Ithenticate Plagiarism and Similarity Checker
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Dr. Deris Stiawan
Date Deposited: 26 Nov 2022 07:04
Last Modified: 26 Nov 2022 07:04
URI: http://repository.unsri.ac.id/id/eprint/82329

Actions (login required)

View Item View Item