UB ScholarWorks

Towards Efficient Features Dimensionality Reduction for Network Intrusion Detection on Highly Imbalanced Traffic

Show simple item record

dc.contributor.author Abdulhammed, Razan
dc.contributor.author Musafer, Hassan
dc.contributor.author Faezipour, Miad
dc.contributor.author Abuzneid, Abdelshakour A.
dc.date.accessioned 2019-05-06T14:41:20Z
dc.date.available 2019-05-06T14:41:20Z
dc.date.issued 2019-03-29
dc.identifier.uri https://scholarworks.bridgeport.edu/xmlui/handle/123456789/4137
dc.description.abstract The performance of an IDS is significantly improved when the features are more discriminative and representative. This research effort is able to reduce the CICIDS2017 dataset’s feature dimensions from 81 to 10, while maintaining a high accuracy of 99.6% in multi-class and binary classification. Furthermore, we propose a Multi-Class Combined performance metric CombinedMc with respect to class distribution to compare various multi-class and binary classification systems through incorporating FAR, DR, Accuracy, and class distribution parameters. In addition, we developed a uniform distribution based balancing approach to handle the imbalanced distribution of the minority class instances in the CICIDS 2017 network intrusion dataset. en_US
dc.language.iso en_US en_US
dc.subject CICIDS2017 en_US
dc.subject Intrusion detection system en_US
dc.subject Network intrusion detection en_US
dc.title Towards Efficient Features Dimensionality Reduction for Network Intrusion Detection on Highly Imbalanced Traffic en_US
dc.type Other en_US
dc.institute.department School of Engineering en_US
dc.institute.name University of Bridgeport en_US
dc.event.location Bridgeport, CT en_US
dc.event.name Faculty Research Day en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search ScholarWorks


Advanced Search

Browse

My Account