The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Insider Threat Detection Using Supervised Machine Learning Algorithms on an Extremely Imbalanced Dataset
|
Author(s): Naghmeh Moradpoor Sheykhkanloo (Edinburgh Napier University, Edinburgh, UK)and Adam Hall (Edinburgh Napier University, Edinburgh, UK)
Copyright: 2020
Volume: 10
Issue: 2
Pages: 26
Source title:
International Journal of Cyber Warfare and Terrorism (IJCWT)
Editor(s)-in-Chief: Brett van Niekerk (University of KwaZulu-Natal, South Africa)
DOI: 10.4018/IJCWT.2020040101
Purchase
|
Abstract
An insider threat can take on many forms and fall under different categories. This includes malicious insider, careless/unaware/uneducated/naïve employee, and the third-party contractor. Machine learning techniques have been studied in published literature as a promising solution for such threats. However, they can be biased and/or inaccurate when the associated dataset is hugely imbalanced. Therefore, this article addresses the insider threat detection on an extremely imbalanced dataset which includes employing a popular balancing technique known as spread subsample. The results show that although balancing the dataset using this technique did not improve performance metrics, it did improve the time taken to build the model and the time taken to test the model. Additionally, the authors realised that running the chosen classifiers with parameters other than the default ones has an impact on both balanced and imbalanced scenarios, but the impact is significantly stronger when using the imbalanced dataset.
Related Content
Nesrine Dardouri, Abdelkader Aguir, Mounir Smida.
© 2024.
20 pages.
|
Tshepo Solomon Raphiri, Joey J. Jansen van Vuuren, Albertus A. K. Buitendag.
© 2023.
20 pages.
|
Timothy Lee Jones.
© 2023.
20 pages.
|
Lev Topor, Moran Pollack.
© 2022.
17 pages.
|
Loo Seng Neo.
© 2022.
15 pages.
|
Maximiliano Emanuel Korstanje.
© 2022.
14 pages.
|
Ben Stewart S., Dhanush N., Santhosh G., Angelin Gladston.
© 2022.
24 pages.
|
|
|