Machine Learning for Network Intrusion Detection—A Comparative Study
Future Internet · 16.07.2023 · 15 (7) · 243
DOI: 10.3390/fi15070243 ↗Kurz gefasst
Fachartikel in der Zeitschrift Future Internet, online erschienen am 16.07.2023. Verfasst von Mustafa Al Lail und 2 weiteren Autor:innen. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Texas A&M International University, National Science Foundation.
Abstract (Originalsprache)
Modern society has quickly evolved to utilize communication and data-sharing media with the advent of the internet and electronic technologies. However, these technologies have created new opportunities for attackers to gain access to confidential electronic resources. As a result, data breaches have significantly impacted our society in multiple ways. To mitigate this situation, researchers have developed multiple security countermeasure techniques known as Network Intrusion Detection Systems (NIDS). Despite these techniques, attackers have developed new strategies to gain unauthorized access to resources. In this work, we propose using machine learning (ML) to develop a NIDS system capable of detecting modern attack types with a very high detection rate. To this end, we implement and evaluate several ML algorithms and compare their effectiveness using a state-of-the-art dataset containing modern attack types. The results show that the random forest model outperforms other models, with a detection rate of modern network attacks of 97 percent. This study shows that not only is accurate prediction possible but also a high detection rate of attacks can be achieved. These results indicate that ML has the potential to create very effective NIDS systems.
Förderung
- Texas A&M International University
- National Science Foundation
Zitieren
APA
Lail, M. A., Garcia, A., & Olivo, S. (2023). Machine Learning for Network Intrusion Detection—A Comparative Study. Future Internet, 15(7), 243. https://doi.org/10.3390/fi15070243
Vancouver
Lail MA, Garcia A, Olivo S. Machine Learning for Network Intrusion Detection—A Comparative Study. Future Internet. 2023;15(7):243. doi:10.3390/fi15070243
BibTeX
@article{Lail2023,
author = {Lail, Mustafa Al and Garcia, Alejandro and Olivo, Saul},
title = {Machine Learning for Network Intrusion Detection—A Comparative Study},
journal = {Future Internet},
year = {2023},
volume = {15},
number = {7},
pages = {243},
doi = {10.3390/fi15070243}
}
EUVIMED