BGP Anomaly Detection with Balanced Datasets

Једноставна страница ставке
dc.citation.epage775
dc.citation.spage766
dc.citation.volume25
dc.contributor.authorOBRADOVIĆ, Slobodan
dc.contributor.authorĆOSOVIĆ, Marijana
dc.date.accessioned2023-07-20T10:42:03Z
dc.date.available2023-07-20T10:42:03Z
dc.date.issued2018
dc.description.abstractWe use machine learning techniques to build predictive models for anomaly detection in the Border Gateway Protocol (BGP). Imbalanced datasets of network anomalies pose limitations to building predictive models for anomaly detection. In order to achieve better classification performance measures, we use resampling methods to balance classes in the datasets. We use undersampling, oversampling and combination techniques to change class distributions of the datasets. In this paper we build predictive models based on preprocessed network anomaly datasets of known Internet network anomalies and observe improvement in classifier performance measures compared to those reported in our previous work. We propose to use resampling combination techniques on datasets along with Decision Tree and Naïve Bayes classifiers in order to achieve the best trade-off between (1) the F-measure and the length of model training time, and (2) avoiding overfitting and loss of information
dc.identifier.doi10.17559/TV-20170219114900
dc.identifier.urihttps://vaseljena.ues.rs.ba/handle/123456789/507
dc.language.isoen
dc.publisherUniversity of Osijek
dc.sourceTechnical Gazette
dc.subjectanomaly detection; BGP; classification; sampling techniques
dc.titleBGP Anomaly Detection with Balanced Datasets
dc.typeArticle
Датотеке
Оригинални завежљај
Сада се приказује 1 - 1 од 1
Сличица
Име:
BGP Anomaly Detection with Balanced Datasets.pdf
Величина:
1.45 MB
Формат:
Adobe Portable Document Format
Опис:
Преузимање
Свежањ лиценце
Сада се приказује 1 - 1 од 1
Сличица
Име:
license.txt
Величина:
1.71 KB
Формат:
Item-specific license agreed to upon submission
Опис:
Преузимање
Колекције
Електротехнички факултет [Научни радови] / Faculty of Electrical Engineering [Scientific papers]