hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20170219114900

BGP Anomaly Detection with Balanced Datasets

Marijana Ćosović ; Faculty of Electrical Engineering, University of East Sarajevo, Vuka Karadzića 30, 71123 East Sarajevo, B&H
Slobodan Obradović ; Faculty of Electrical Engineering, University of East Sarajevo, Vuka Karadzića 30, 71123 East Sarajevo, B&H

Puni tekst: engleski, pdf (1 MB) str. 766-775 preuzimanja: 190* citiraj
APA 6th Edition
Ćosović, M. i Obradović, S. (2018). BGP Anomaly Detection with Balanced Datasets. Tehnički vjesnik, 25 (3), 766-775. https://doi.org/10.17559/TV-20170219114900
MLA 8th Edition
Ćosović, Marijana i Slobodan Obradović. "BGP Anomaly Detection with Balanced Datasets." Tehnički vjesnik, vol. 25, br. 3, 2018, str. 766-775. https://doi.org/10.17559/TV-20170219114900. Citirano 13.11.2019.
Chicago 17th Edition
Ćosović, Marijana i Slobodan Obradović. "BGP Anomaly Detection with Balanced Datasets." Tehnički vjesnik 25, br. 3 (2018): 766-775. https://doi.org/10.17559/TV-20170219114900
Harvard
Ćosović, M., i Obradović, S. (2018). 'BGP Anomaly Detection with Balanced Datasets', Tehnički vjesnik, 25(3), str. 766-775. https://doi.org/10.17559/TV-20170219114900
Vancouver
Ćosović M, Obradović S. BGP Anomaly Detection with Balanced Datasets. Tehnički vjesnik [Internet]. 2018 [pristupljeno 13.11.2019.];25(3):766-775. https://doi.org/10.17559/TV-20170219114900
IEEE
M. Ćosović i S. Obradović, "BGP Anomaly Detection with Balanced Datasets", Tehnički vjesnik, vol.25, br. 3, str. 766-775, 2018. [Online]. https://doi.org/10.17559/TV-20170219114900

Sažetak
We 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.

Ključne riječi
anomaly detection; BGP; classification; sampling techniques

Hrčak ID: 202619

URI
https://hrcak.srce.hr/202619

Posjeta: 344 *