Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201364216> ?p ?o ?g. }
- W3201364216 endingPage "129647" @default.
- W3201364216 startingPage "129635" @default.
- W3201364216 abstract "A network intrusion detection (NID) system plays a critical role in cybersecurity. However, the existing machine learning-based NID research has a vital issue that their experimental settings do not reflect real-world situations where unknown attacks are constantly emerging. In particular, their train and test sets are from a single data set, which inevitably overestimates the detection power since all test attack types are known in training, and test cases will have similar characteristics to the training data. This paper introduces a new strategy to constitute test data with updated traffic with attack types not included in training data. In the proposed setting, the prediction accuracy of the existing detectors is dropped by about 20% compared to what has been reported. Also, in-depth analysis of detection performance by attack types has revealed that the existing models have strength at certain attack types but struggle to detect the other attack types such as DoS, DDoS, web attack, and port scan. To overcome the issues, we propose a new neural detector, called MHSA, based on a multi-head self-attention mechanism whose architecture suits better to capture scattered pieces of evidence in network traffic. Our model improved the overall detection performance by 29% in false positive rate at the true positive rate of 0.9 and by 9% in AUC over the current state-of-the-art models, successfully detecting the attacks that are not well captured before. Furthermore, we show that our proposed MHSA model even outperforms the best ensemble detector constructed by joining the state-of-the-art classifiers." @default.
- W3201364216 created "2021-09-27" @default.
- W3201364216 creator A5011038151 @default.
- W3201364216 creator A5017436583 @default.
- W3201364216 creator A5028060473 @default.
- W3201364216 creator A5046513588 @default.
- W3201364216 creator A5054307157 @default.
- W3201364216 creator A5076200886 @default.
- W3201364216 creator A5077894846 @default.
- W3201364216 date "2021-01-01" @default.
- W3201364216 modified "2023-09-26" @default.
- W3201364216 title "Hunt for Unseen Intrusion: Multi-Head Self-Attention Neural Detector" @default.
- W3201364216 cites W1510025668 @default.
- W3201364216 cites W1930624869 @default.
- W3201364216 cites W1996799478 @default.
- W3201364216 cites W2031163547 @default.
- W3201364216 cites W2056132907 @default.
- W3201364216 cites W2099940443 @default.
- W3201364216 cites W2120716184 @default.
- W3201364216 cites W2142889610 @default.
- W3201364216 cites W2155806188 @default.
- W3201364216 cites W2296509296 @default.
- W3201364216 cites W2331488455 @default.
- W3201364216 cites W2408350275 @default.
- W3201364216 cites W2460037574 @default.
- W3201364216 cites W2470673105 @default.
- W3201364216 cites W2512144135 @default.
- W3201364216 cites W2532764181 @default.
- W3201364216 cites W2576364334 @default.
- W3201364216 cites W2606697812 @default.
- W3201364216 cites W2742495185 @default.
- W3201364216 cites W2743678626 @default.
- W3201364216 cites W2751639377 @default.
- W3201364216 cites W2752782242 @default.
- W3201364216 cites W2772317693 @default.
- W3201364216 cites W2783741806 @default.
- W3201364216 cites W2786585314 @default.
- W3201364216 cites W2789828921 @default.
- W3201364216 cites W2794310334 @default.
- W3201364216 cites W2798790152 @default.
- W3201364216 cites W2799548584 @default.
- W3201364216 cites W2803414046 @default.
- W3201364216 cites W2809211248 @default.
- W3201364216 cites W2889165715 @default.
- W3201364216 cites W2892556724 @default.
- W3201364216 cites W2909665293 @default.
- W3201364216 cites W2914206419 @default.
- W3201364216 cites W2921453769 @default.
- W3201364216 cites W2925211503 @default.
- W3201364216 cites W2941716987 @default.
- W3201364216 cites W2944992190 @default.
- W3201364216 cites W2955240225 @default.
- W3201364216 cites W2969295985 @default.
- W3201364216 cites W2982084047 @default.
- W3201364216 cites W3005630930 @default.
- W3201364216 cites W3015177549 @default.
- W3201364216 cites W3035160371 @default.
- W3201364216 cites W4239510810 @default.
- W3201364216 cites W4248437541 @default.
- W3201364216 doi "https://doi.org/10.1109/access.2021.3113124" @default.
- W3201364216 hasPublicationYear "2021" @default.
- W3201364216 type Work @default.
- W3201364216 sameAs 3201364216 @default.
- W3201364216 citedByCount "2" @default.
- W3201364216 countsByYear W32013642162023 @default.
- W3201364216 crossrefType "journal-article" @default.
- W3201364216 hasAuthorship W3201364216A5011038151 @default.
- W3201364216 hasAuthorship W3201364216A5017436583 @default.
- W3201364216 hasAuthorship W3201364216A5028060473 @default.
- W3201364216 hasAuthorship W3201364216A5046513588 @default.
- W3201364216 hasAuthorship W3201364216A5054307157 @default.
- W3201364216 hasAuthorship W3201364216A5076200886 @default.
- W3201364216 hasAuthorship W3201364216A5077894846 @default.
- W3201364216 hasBestOaLocation W32013642161 @default.
- W3201364216 hasConcept C108583219 @default.
- W3201364216 hasConcept C119857082 @default.
- W3201364216 hasConcept C124101348 @default.
- W3201364216 hasConcept C154945302 @default.
- W3201364216 hasConcept C165696696 @default.
- W3201364216 hasConcept C16910744 @default.
- W3201364216 hasConcept C177264268 @default.
- W3201364216 hasConcept C199360897 @default.
- W3201364216 hasConcept C35525427 @default.
- W3201364216 hasConcept C38652104 @default.
- W3201364216 hasConcept C41008148 @default.
- W3201364216 hasConcept C50644808 @default.
- W3201364216 hasConcept C51632099 @default.
- W3201364216 hasConcept C58489278 @default.
- W3201364216 hasConcept C76155785 @default.
- W3201364216 hasConcept C94915269 @default.
- W3201364216 hasConcept C95922358 @default.
- W3201364216 hasConceptScore W3201364216C108583219 @default.
- W3201364216 hasConceptScore W3201364216C119857082 @default.
- W3201364216 hasConceptScore W3201364216C124101348 @default.
- W3201364216 hasConceptScore W3201364216C154945302 @default.
- W3201364216 hasConceptScore W3201364216C165696696 @default.
- W3201364216 hasConceptScore W3201364216C16910744 @default.
- W3201364216 hasConceptScore W3201364216C177264268 @default.