FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044356985> ?p ?o ?g. }

• W3044356985 endingPage "134497" @default.
• W3044356985 startingPage "134480" @default.
• W3044356985 abstract "The global surge of cyber-attacks in the form of sequential network attacks has propelled the need for robust intrusion detection and prediction systems. Such attacks are difficult to reveal using current intrusion detection systems, since each individual attack phase may appear benign when examined outside of its context. In addition, there are challenges in building supervised learning models for such attacks, since there are limited labelled datasets available. Hence, there is a need for updating already built models to specific operational environments and for addressing the concept drift. A hidden Markov model (HMM) is a popular framework for sequential modelling, however, in addition to the above challenges, the model parameters are difficult to optimise. This paper proposes a transfer learning (TL) approach that exploits already learned knowledge, gained from a labelled source dataset, and adapts it on a different, unlabelled target dataset. The datasets may be from a different but related domain. Five unsupervised HMM techniques are developed utilising a TL approach and evaluated against conventional machine learning approaches. Baum-Welch (BW), Viterbi training, gradient descent, differential evolution (DE) and simulated annealing, are deployed for the detection of attack stages in the network traffic, as well as, forecasting both the next most probable attack stage and its method of manifestation. Specifically, for the prediction of the three next most likely states and observations, TL with DE achieved a maximum accuracy improvement of 48.3%, and 27.4%, respectively. Finally, the actual detection prediction for the three next most probable states and methods of manifestation reaches 78.9% and 96.3% using TL with BW and DE, respectively." @default.
• W3044356985 created "2020-07-29" @default.
• W3044356985 creator A5009232291 @default.
• W3044356985 creator A5043588709 @default.
• W3044356985 creator A5046799023 @default.
• W3044356985 date "2020-01-01" @default.
• W3044356985 modified "2023-10-18" @default.
• W3044356985 title "Learning to Learn Sequential Network Attacks Using Hidden Markov Models" @default.
• W3044356985 cites W1498207715 @default.
• W3044356985 cites W1842326261 @default.
• W3044356985 cites W1912236669 @default.
• W3044356985 cites W2036699304 @default.
• W3044356985 cites W2077249246 @default.
• W3044356985 cites W2111124271 @default.
• W3044356985 cites W2125838338 @default.
• W3044356985 cites W2144996578 @default.
• W3044356985 cites W2163345210 @default.
• W3044356985 cites W2165698076 @default.
• W3044356985 cites W2171850596 @default.
• W3044356985 cites W2418667810 @default.
• W3044356985 cites W2479608706 @default.
• W3044356985 cites W2536179434 @default.
• W3044356985 cites W2609042334 @default.
• W3044356985 cites W2613954013 @default.
• W3044356985 cites W2755588949 @default.
• W3044356985 cites W2789828921 @default.
• W3044356985 cites W2917681175 @default.
• W3044356985 cites W2940934424 @default.
• W3044356985 cites W2952292163 @default.
• W3044356985 cites W2959653735 @default.
• W3044356985 cites W2969482453 @default.
• W3044356985 cites W2982379385 @default.
• W3044356985 cites W2993751684 @default.
• W3044356985 cites W3010216764 @default.
• W3044356985 cites W4235169531 @default.
• W3044356985 doi "https://doi.org/10.1109/access.2020.3011293" @default.
• W3044356985 hasPublicationYear "2020" @default.
• W3044356985 type Work @default.
• W3044356985 sameAs 3044356985 @default.
• W3044356985 citedByCount "10" @default.
• W3044356985 countsByYear W30443569852021 @default.
• W3044356985 countsByYear W30443569852022 @default.
• W3044356985 countsByYear W30443569852023 @default.
• W3044356985 crossrefType "journal-article" @default.
• W3044356985 hasAuthorship W3044356985A5009232291 @default.
• W3044356985 hasAuthorship W3044356985A5043588709 @default.
• W3044356985 hasAuthorship W3044356985A5046799023 @default.
• W3044356985 hasBestOaLocation W30443569851 @default.
• W3044356985 hasConcept C108583219 @default.
• W3044356985 hasConcept C119857082 @default.
• W3044356985 hasConcept C124101348 @default.
• W3044356985 hasConcept C150899416 @default.
• W3044356985 hasConcept C151730666 @default.
• W3044356985 hasConcept C154945302 @default.
• W3044356985 hasConcept C165696696 @default.
• W3044356985 hasConcept C23224414 @default.
• W3044356985 hasConcept C2779343474 @default.
• W3044356985 hasConcept C35525427 @default.
• W3044356985 hasConcept C38652104 @default.
• W3044356985 hasConcept C41008148 @default.
• W3044356985 hasConcept C60582962 @default.
• W3044356985 hasConcept C86803240 @default.
• W3044356985 hasConceptScore W3044356985C108583219 @default.
• W3044356985 hasConceptScore W3044356985C119857082 @default.
• W3044356985 hasConceptScore W3044356985C124101348 @default.
• W3044356985 hasConceptScore W3044356985C150899416 @default.
• W3044356985 hasConceptScore W3044356985C151730666 @default.
• W3044356985 hasConceptScore W3044356985C154945302 @default.
• W3044356985 hasConceptScore W3044356985C165696696 @default.
• W3044356985 hasConceptScore W3044356985C23224414 @default.
• W3044356985 hasConceptScore W3044356985C2779343474 @default.
• W3044356985 hasConceptScore W3044356985C35525427 @default.
• W3044356985 hasConceptScore W3044356985C38652104 @default.
• W3044356985 hasConceptScore W3044356985C41008148 @default.
• W3044356985 hasConceptScore W3044356985C60582962 @default.
• W3044356985 hasConceptScore W3044356985C86803240 @default.
• W3044356985 hasFunder F4320334627 @default.
• W3044356985 hasLocation W30443569851 @default.
• W3044356985 hasLocation W30443569852 @default.
• W3044356985 hasOpenAccess W3044356985 @default.
• W3044356985 hasPrimaryLocation W30443569851 @default.
• W3044356985 hasRelatedWork W1975869217 @default.
• W3044356985 hasRelatedWork W2116722627 @default.
• W3044356985 hasRelatedWork W2129150969 @default.
• W3044356985 hasRelatedWork W2136652457 @default.
• W3044356985 hasRelatedWork W2160171981 @default.
• W3044356985 hasRelatedWork W2169849734 @default.
• W3044356985 hasRelatedWork W2379938888 @default.
• W3044356985 hasRelatedWork W2383829109 @default.
• W3044356985 hasRelatedWork W2385954530 @default.
• W3044356985 hasRelatedWork W2401728283 @default.
• W3044356985 hasVolume "8" @default.
• W3044356985 isParatext "false" @default.
• W3044356985 isRetracted "false" @default.
• W3044356985 magId "3044356985" @default.
• W3044356985 workType "article" @default.