Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318604528> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4318604528 abstract "Machine learning (ML) on graph-structured data has recently received deepened interest in the context of intrusion detection in the cybersecurity domain. Due to the increasing amounts of data generated by monitoring tools as well as more and more sophisticated attacks, these ML methods are gaining traction. Knowledge graphs and their corresponding learning techniques such as Graph Neural Networks (GNNs) with their ability to seamlessly integrate data from multiple domains using human-understandable vocabularies, are finding application in the cybersecurity domain. However, similar to other connectionist models, GNNs are lacking transparency in their decision making. This is especially important as there tend to be a high number of false positive alerts in the cybersecurity domain, such that triage needs to be done by domain experts, requiring a lot of man power. Therefore, we are addressing Explainable AI (XAI) for GNNs to enhance trust management by exploring combining symbolic and sub-symbolic methods in the area of cybersecurity that incorporate domain knowledge. We experimented with this approach by generating explanations in an industrial demonstrator system. The proposed method is shown to produce intuitive explanations for alerts for a diverse range of scenarios. Not only do the explanations provide deeper insights into the alerts, but they also lead to a reduction of false positive alerts by 66% and by 93% when including the fidelity metric." @default.
- W4318604528 created "2023-01-31" @default.
- W4318604528 creator A5002518694 @default.
- W4318604528 creator A5017846984 @default.
- W4318604528 creator A5042654410 @default.
- W4318604528 creator A5044187928 @default.
- W4318604528 creator A5063752112 @default.
- W4318604528 date "2022-12-04" @default.
- W4318604528 modified "2023-10-18" @default.
- W4318604528 title "Detection, Explanation and Filtering of Cyber Attacks Combining Symbolic and Sub-Symbolic Methods" @default.
- W4318604528 cites W2261812172 @default.
- W4318604528 cites W2780131526 @default.
- W4318604528 cites W2979481854 @default.
- W4318604528 cites W2980659949 @default.
- W4318604528 cites W2997610263 @default.
- W4318604528 cites W3012972431 @default.
- W4318604528 cites W3017312168 @default.
- W4318604528 cites W3090540360 @default.
- W4318604528 cites W3091163785 @default.
- W4318604528 cites W3094828954 @default.
- W4318604528 cites W3198760505 @default.
- W4318604528 cites W4200630125 @default.
- W4318604528 cites W4238948521 @default.
- W4318604528 cites W2990718118 @default.
- W4318604528 doi "https://doi.org/10.1109/ssci51031.2022.10022249" @default.
- W4318604528 hasPublicationYear "2022" @default.
- W4318604528 type Work @default.
- W4318604528 citedByCount "0" @default.
- W4318604528 crossrefType "proceedings-article" @default.
- W4318604528 hasAuthorship W4318604528A5002518694 @default.
- W4318604528 hasAuthorship W4318604528A5017846984 @default.
- W4318604528 hasAuthorship W4318604528A5042654410 @default.
- W4318604528 hasAuthorship W4318604528A5044187928 @default.
- W4318604528 hasAuthorship W4318604528A5063752112 @default.
- W4318604528 hasBestOaLocation W43186045282 @default.
- W4318604528 hasConcept C119857082 @default.
- W4318604528 hasConcept C124101348 @default.
- W4318604528 hasConcept C134306372 @default.
- W4318604528 hasConcept C151730666 @default.
- W4318604528 hasConcept C154945302 @default.
- W4318604528 hasConcept C2779343474 @default.
- W4318604528 hasConcept C33923547 @default.
- W4318604528 hasConcept C35525427 @default.
- W4318604528 hasConcept C36503486 @default.
- W4318604528 hasConcept C38652104 @default.
- W4318604528 hasConcept C41008148 @default.
- W4318604528 hasConcept C86803240 @default.
- W4318604528 hasConceptScore W4318604528C119857082 @default.
- W4318604528 hasConceptScore W4318604528C124101348 @default.
- W4318604528 hasConceptScore W4318604528C134306372 @default.
- W4318604528 hasConceptScore W4318604528C151730666 @default.
- W4318604528 hasConceptScore W4318604528C154945302 @default.
- W4318604528 hasConceptScore W4318604528C2779343474 @default.
- W4318604528 hasConceptScore W4318604528C33923547 @default.
- W4318604528 hasConceptScore W4318604528C35525427 @default.
- W4318604528 hasConceptScore W4318604528C36503486 @default.
- W4318604528 hasConceptScore W4318604528C38652104 @default.
- W4318604528 hasConceptScore W4318604528C41008148 @default.
- W4318604528 hasConceptScore W4318604528C86803240 @default.
- W4318604528 hasLocation W43186045281 @default.
- W4318604528 hasLocation W43186045282 @default.
- W4318604528 hasOpenAccess W4318604528 @default.
- W4318604528 hasPrimaryLocation W43186045281 @default.
- W4318604528 hasRelatedWork W2351252967 @default.
- W4318604528 hasRelatedWork W2366221835 @default.
- W4318604528 hasRelatedWork W2373866020 @default.
- W4318604528 hasRelatedWork W2377933504 @default.
- W4318604528 hasRelatedWork W2388271354 @default.
- W4318604528 hasRelatedWork W2584408238 @default.
- W4318604528 hasRelatedWork W2961085424 @default.
- W4318604528 hasRelatedWork W4205568523 @default.
- W4318604528 hasRelatedWork W4285337355 @default.
- W4318604528 hasRelatedWork W4306674287 @default.
- W4318604528 isParatext "false" @default.
- W4318604528 isRetracted "false" @default.
- W4318604528 workType "article" @default.