FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202908052> ?p ?o ?g. }

• W3202908052 abstract "The standard ML methodology assumes that the test samples are derived from a set of pre-observed classes used in the training phase. Where the model extracts and learns useful patterns to detect new data samples belonging to the same data classes. However, in certain applications such as Network Intrusion Detection Systems, it is challenging to obtain data samples for all attack classes that the model will most likely observe in production. ML-based NIDSs face new attack traffic known as zero-day attacks, that are not used in the training of the learning models due to their non-existence at the time. In this paper, a zero-shot learning methodology has been proposed to evaluate the ML model performance in the detection of zero-day attack scenarios. In the attribute learning stage, the ML models map the network data features to distinguish semantic attributes from known attack (seen) classes. In the inference stage, the models are evaluated in the detection of zero-day attack (unseen) classes by constructing the relationships between known attacks and zero-day attacks. A new metric is defined as Zero-day Detection Rate, which measures the effectiveness of the learning model in the inference stage. The results demonstrate that while the majority of the attack classes do not represent significant risks to organisations adopting an ML-based NIDS in a zero-day attack scenario. However, for certain attack groups identified in this paper, such systems are not effective in applying the learnt attributes of attack behaviour to detect them as malicious. Further Analysis was conducted using the Wasserstein Distance technique to measure how different such attacks are from other attack types used in the training of the ML model. The results demonstrate that sophisticated attacks with a low zero-day detection rate have a significantly distinct feature distribution compared to the other attack classes." @default.
• W3202908052 created "2021-10-11" @default.
• W3202908052 creator A5016369735 @default.
• W3202908052 creator A5017810911 @default.
• W3202908052 creator A5047926199 @default.
• W3202908052 creator A5078468070 @default.
• W3202908052 date "2022-01-01" @default.
• W3202908052 modified "2023-09-25" @default.
• W3202908052 title "From Zero-Shot Machine Learning to Zero-Day Attack Detection" @default.
• W3202908052 cites W1494192115 @default.
• W3202908052 cites W1530215515 @default.
• W3202908052 cites W1679074130 @default.
• W3202908052 cites W1812927916 @default.
• W3202908052 cites W1975415766 @default.
• W3202908052 cites W1985987493 @default.
• W3202908052 cites W2046163812 @default.
• W3202908052 cites W2065890363 @default.
• W3202908052 cites W2117646649 @default.
• W3202908052 cites W2118023920 @default.
• W3202908052 cites W2142889610 @default.
• W3202908052 cites W2176028050 @default.
• W3202908052 cites W2342408547 @default.
• W3202908052 cites W2535159308 @default.
• W3202908052 cites W2596142952 @default.
• W3202908052 cites W2761152885 @default.
• W3202908052 cites W2861867928 @default.
• W3202908052 cites W2897620540 @default.
• W3202908052 cites W2910453440 @default.
• W3202908052 cites W2911964244 @default.
• W3202908052 cites W2922140331 @default.
• W3202908052 cites W2922628727 @default.
• W3202908052 cites W2945867651 @default.
• W3202908052 cites W2962688977 @default.
• W3202908052 cites W2967369756 @default.
• W3202908052 cites W2970501769 @default.
• W3202908052 cites W2996563683 @default.
• W3202908052 cites W3092771185 @default.
• W3202908052 cites W3097159718 @default.
• W3202908052 cites W3105682467 @default.
• W3202908052 cites W3125372392 @default.
• W3202908052 cites W3157020971 @default.
• W3202908052 cites W33506368 @default.
• W3202908052 doi "https://doi.org/10.2139/ssrn.4029439" @default.
• W3202908052 hasPublicationYear "2022" @default.
• W3202908052 type Work @default.
• W3202908052 sameAs 3202908052 @default.
• W3202908052 citedByCount "0" @default.
• W3202908052 crossrefType "journal-article" @default.
• W3202908052 hasAuthorship W3202908052A5016369735 @default.
• W3202908052 hasAuthorship W3202908052A5017810911 @default.
• W3202908052 hasAuthorship W3202908052A5047926199 @default.
• W3202908052 hasAuthorship W3202908052A5078468070 @default.
• W3202908052 hasBestOaLocation W32029080522 @default.
• W3202908052 hasConcept C121332964 @default.
• W3202908052 hasConcept C138885662 @default.
• W3202908052 hasConcept C154945302 @default.
• W3202908052 hasConcept C176329583 @default.
• W3202908052 hasConcept C178489894 @default.
• W3202908052 hasConcept C185544564 @default.
• W3202908052 hasConcept C191897082 @default.
• W3202908052 hasConcept C192562407 @default.
• W3202908052 hasConcept C2778344882 @default.
• W3202908052 hasConcept C2780518707 @default.
• W3202908052 hasConcept C2780813799 @default.
• W3202908052 hasConcept C38652104 @default.
• W3202908052 hasConcept C41008148 @default.
• W3202908052 hasConcept C41895202 @default.
• W3202908052 hasConceptScore W3202908052C121332964 @default.
• W3202908052 hasConceptScore W3202908052C138885662 @default.
• W3202908052 hasConceptScore W3202908052C154945302 @default.
• W3202908052 hasConceptScore W3202908052C176329583 @default.
• W3202908052 hasConceptScore W3202908052C178489894 @default.
• W3202908052 hasConceptScore W3202908052C185544564 @default.
• W3202908052 hasConceptScore W3202908052C191897082 @default.
• W3202908052 hasConceptScore W3202908052C192562407 @default.
• W3202908052 hasConceptScore W3202908052C2778344882 @default.
• W3202908052 hasConceptScore W3202908052C2780518707 @default.
• W3202908052 hasConceptScore W3202908052C2780813799 @default.
• W3202908052 hasConceptScore W3202908052C38652104 @default.
• W3202908052 hasConceptScore W3202908052C41008148 @default.
• W3202908052 hasConceptScore W3202908052C41895202 @default.
• W3202908052 hasLocation W32029080521 @default.
• W3202908052 hasLocation W32029080522 @default.
• W3202908052 hasLocation W32029080523 @default.
• W3202908052 hasOpenAccess W3202908052 @default.
• W3202908052 hasPrimaryLocation W32029080521 @default.
• W3202908052 hasRelatedWork W2139044314 @default.
• W3202908052 hasRelatedWork W2319835126 @default.
• W3202908052 hasRelatedWork W2582845058 @default.
• W3202908052 hasRelatedWork W2774307855 @default.
• W3202908052 hasRelatedWork W2795757513 @default.
• W3202908052 hasRelatedWork W2972409856 @default.
• W3202908052 hasRelatedWork W3036858000 @default.
• W3202908052 hasRelatedWork W3088560023 @default.
• W3202908052 hasRelatedWork W1815953900 @default.
• W3202908052 hasRelatedWork W2168002573 @default.
• W3202908052 isParatext "false" @default.
• W3202908052 isRetracted "false" @default.
• W3202908052 magId "3202908052" @default.
• W3202908052 workType "article" @default.