Matches in SemOpenAlex for { <https://semopenalex.org/work/W4361296232> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4361296232 endingPage "108692" @default.
- W4361296232 startingPage "108692" @default.
- W4361296232 abstract "Many of the proposed machine learning (ML) based network intrusion detection systems (NIDSs) achieve near perfect detection performance when evaluated on synthetic benchmark datasets. However, there is no record of if and how these results generalise to other network environments. In this paper, we investigate the cross-domain performance of ML-based NIDSs by extensively evaluating eight supervised and unsupervised learning models on four recently published benchmark NIDS datasets. Our investigation indicates that none of the considered models is able to generalise over all studied datasets. Interestingly, our results also indicate that the cross-domain performance has a high degree of asymmetry, i.e., swapping the source and target domains can significantly change the classification performance. Our investigation also indicates that overall, unsupervised learning methods perform better than supervised learning models in our considered scenarios. We further used SHAP values to explain the observed cross-domain performance results. They show a high correlation between a good model performance and a correspondence between feature distributions/values and Attack/Benign classes." @default.
- W4361296232 created "2023-03-31" @default.
- W4361296232 creator A5016369735 @default.
- W4361296232 creator A5078468070 @default.
- W4361296232 date "2023-05-01" @default.
- W4361296232 modified "2023-10-18" @default.
- W4361296232 title "Explainable Cross-domain Evaluation of ML-based Network Intrusion Detection Systems" @default.
- W4361296232 cites W1995443851 @default.
- W4361296232 cites W2064447488 @default.
- W4361296232 cites W2091825929 @default.
- W4361296232 cites W2099940443 @default.
- W4361296232 cites W2134490011 @default.
- W4361296232 cites W2487898712 @default.
- W4361296232 cites W2789828921 @default.
- W4361296232 cites W2901200207 @default.
- W4361296232 cites W2963748489 @default.
- W4361296232 cites W3100989807 @default.
- W4361296232 cites W3211805421 @default.
- W4361296232 doi "https://doi.org/10.1016/j.compeleceng.2023.108692" @default.
- W4361296232 hasPublicationYear "2023" @default.
- W4361296232 type Work @default.
- W4361296232 citedByCount "0" @default.
- W4361296232 crossrefType "journal-article" @default.
- W4361296232 hasAuthorship W4361296232A5016369735 @default.
- W4361296232 hasAuthorship W4361296232A5078468070 @default.
- W4361296232 hasBestOaLocation W43612962322 @default.
- W4361296232 hasConcept C119857082 @default.
- W4361296232 hasConcept C124101348 @default.
- W4361296232 hasConcept C13280743 @default.
- W4361296232 hasConcept C134306372 @default.
- W4361296232 hasConcept C136389625 @default.
- W4361296232 hasConcept C138885662 @default.
- W4361296232 hasConcept C153180895 @default.
- W4361296232 hasConcept C154945302 @default.
- W4361296232 hasConcept C185798385 @default.
- W4361296232 hasConcept C205649164 @default.
- W4361296232 hasConcept C27181475 @default.
- W4361296232 hasConcept C2776401178 @default.
- W4361296232 hasConcept C33923547 @default.
- W4361296232 hasConcept C35525427 @default.
- W4361296232 hasConcept C36503486 @default.
- W4361296232 hasConcept C41008148 @default.
- W4361296232 hasConcept C41895202 @default.
- W4361296232 hasConcept C50644808 @default.
- W4361296232 hasConcept C8038995 @default.
- W4361296232 hasConceptScore W4361296232C119857082 @default.
- W4361296232 hasConceptScore W4361296232C124101348 @default.
- W4361296232 hasConceptScore W4361296232C13280743 @default.
- W4361296232 hasConceptScore W4361296232C134306372 @default.
- W4361296232 hasConceptScore W4361296232C136389625 @default.
- W4361296232 hasConceptScore W4361296232C138885662 @default.
- W4361296232 hasConceptScore W4361296232C153180895 @default.
- W4361296232 hasConceptScore W4361296232C154945302 @default.
- W4361296232 hasConceptScore W4361296232C185798385 @default.
- W4361296232 hasConceptScore W4361296232C205649164 @default.
- W4361296232 hasConceptScore W4361296232C27181475 @default.
- W4361296232 hasConceptScore W4361296232C2776401178 @default.
- W4361296232 hasConceptScore W4361296232C33923547 @default.
- W4361296232 hasConceptScore W4361296232C35525427 @default.
- W4361296232 hasConceptScore W4361296232C36503486 @default.
- W4361296232 hasConceptScore W4361296232C41008148 @default.
- W4361296232 hasConceptScore W4361296232C41895202 @default.
- W4361296232 hasConceptScore W4361296232C50644808 @default.
- W4361296232 hasConceptScore W4361296232C8038995 @default.
- W4361296232 hasFunder F4320321995 @default.
- W4361296232 hasLocation W43612962321 @default.
- W4361296232 hasLocation W43612962322 @default.
- W4361296232 hasLocation W43612962323 @default.
- W4361296232 hasOpenAccess W4361296232 @default.
- W4361296232 hasPrimaryLocation W43612962321 @default.
- W4361296232 hasRelatedWork W143775194 @default.
- W4361296232 hasRelatedWork W2057778272 @default.
- W4361296232 hasRelatedWork W2130121108 @default.
- W4361296232 hasRelatedWork W2986085304 @default.
- W4361296232 hasRelatedWork W3047177827 @default.
- W4361296232 hasRelatedWork W3080681248 @default.
- W4361296232 hasRelatedWork W3148060700 @default.
- W4361296232 hasRelatedWork W4287685660 @default.
- W4361296232 hasRelatedWork W4319302697 @default.
- W4361296232 hasRelatedWork W4376646226 @default.
- W4361296232 hasVolume "108" @default.
- W4361296232 isParatext "false" @default.
- W4361296232 isRetracted "false" @default.
- W4361296232 workType "article" @default.