Matches in SemOpenAlex for { <https://semopenalex.org/work/W4297984369> ?p ?o ?g. }
Showing items 1 to 60 of
60
with 100 items per page.
- W4297984369 endingPage "102940" @default.
- W4297984369 startingPage "102940" @default.
- W4297984369 abstract "As the amount of traffic on the Internet increases, so does the number of new and sophisticated network attacks. Intrusion detection systems are the most important tools for accurate detection of potential threats. Due to the dynamic nature of network attacks, deep learning neural networks play a significant role in intrusion detection, as they have proven to be effective in processing large amounts of data. However, deep learning networks often have difficulties to effectively detect attack classes that are in minority, when trained with imbalanced cybersecurity data. The common way to deal with this difficulty is resampling. In contrast to resampling, in this paper we implement Deep Neural Network for intrusion detection varying its parameters, and analyse detection performances of minority classes in imbalanced multi-class data. The model is trained and tested on the CICIDS-2017 dataset, which contains almost 3 million records and 15 traffic classes, where some classes are in extreme minority, holding only a few records per class. Additionally, the model was evaluated on an also imbalanced CICIDS-2018 dataset. Two feature selection methods are performed on the preprocessed data, in order to obtain two different feature subsets. Our findings show that some coarse grained features are of such significance that attacks with only 3 instances can be completely and accurately detected. As a conclusion, we show the difference in feature characteristics for minority classes that are crucial for their detection." @default.
- W4297984369 created "2022-10-01" @default.
- W4297984369 creator A5051641618 @default.
- W4297984369 creator A5070597967 @default.
- W4297984369 date "2022-12-01" @default.
- W4297984369 modified "2023-09-29" @default.
- W4297984369 title "Extreme minority class detection in imbalanced data for network intrusion" @default.
- W4297984369 cites W2790583291 @default.
- W4297984369 cites W3043530913 @default.
- W4297984369 cites W3047132966 @default.
- W4297984369 cites W3113154577 @default.
- W4297984369 cites W3134696756 @default.
- W4297984369 cites W3197150995 @default.
- W4297984369 cites W3205323312 @default.
- W4297984369 doi "https://doi.org/10.1016/j.cose.2022.102940" @default.
- W4297984369 hasPublicationYear "2022" @default.
- W4297984369 type Work @default.
- W4297984369 citedByCount "4" @default.
- W4297984369 countsByYear W42979843692023 @default.
- W4297984369 crossrefType "journal-article" @default.
- W4297984369 hasAuthorship W4297984369A5051641618 @default.
- W4297984369 hasAuthorship W4297984369A5070597967 @default.
- W4297984369 hasConcept C124101348 @default.
- W4297984369 hasConcept C127313418 @default.
- W4297984369 hasConcept C154945302 @default.
- W4297984369 hasConcept C158251709 @default.
- W4297984369 hasConcept C17409809 @default.
- W4297984369 hasConcept C2777212361 @default.
- W4297984369 hasConcept C35525427 @default.
- W4297984369 hasConcept C38652104 @default.
- W4297984369 hasConcept C41008148 @default.
- W4297984369 hasConceptScore W4297984369C124101348 @default.
- W4297984369 hasConceptScore W4297984369C127313418 @default.
- W4297984369 hasConceptScore W4297984369C154945302 @default.
- W4297984369 hasConceptScore W4297984369C158251709 @default.
- W4297984369 hasConceptScore W4297984369C17409809 @default.
- W4297984369 hasConceptScore W4297984369C2777212361 @default.
- W4297984369 hasConceptScore W4297984369C35525427 @default.
- W4297984369 hasConceptScore W4297984369C38652104 @default.
- W4297984369 hasConceptScore W4297984369C41008148 @default.
- W4297984369 hasFunder F4320322729 @default.
- W4297984369 hasLocation W42979843691 @default.
- W4297984369 hasOpenAccess W4297984369 @default.
- W4297984369 hasPrimaryLocation W42979843691 @default.
- W4297984369 hasRelatedWork W2037496939 @default.
- W4297984369 hasRelatedWork W2121378079 @default.
- W4297984369 hasRelatedWork W2355783318 @default.
- W4297984369 hasRelatedWork W2366221835 @default.
- W4297984369 hasRelatedWork W2378891550 @default.
- W4297984369 hasRelatedWork W2385987727 @default.
- W4297984369 hasRelatedWork W2387829579 @default.
- W4297984369 hasRelatedWork W2388271354 @default.
- W4297984369 hasRelatedWork W2394110669 @default.
- W4297984369 hasRelatedWork W4376624795 @default.
- W4297984369 hasVolume "123" @default.
- W4297984369 isParatext "false" @default.
- W4297984369 isRetracted "false" @default.
- W4297984369 workType "article" @default.