Matches in SemOpenAlex for { <https://semopenalex.org/work/W3080405556> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3080405556 abstract "Deep learning is increasingly used as a building block of security systems. Unfortunately, neural networks are hard to interpret and typically opaque to the practitioner. The machine learning community has started to address this problem by developing methods for explaining the predictions of neural networks. While several of these approaches have been successfully applied in the area of computer vision, their application in security has received little attention so far. It is an open question which explanation methods are appropriate for computer security and what requirements they need to satisfy.In this paper, we introduce criteria for comparing and evaluating explanation methods in the context of computer security. These cover general properties, such as the accuracy of explanations, as well as security-focused aspects, such as the completeness, efficiency, and robustness. Based on our criteria, we investigate six popular explanation methods and assess their utility in security systems for malware detection and vulnerability discovery. We observe significant differences between the methods and build on these to derive general recommendations for selecting and applying explanation methods in computer security." @default.
- W3080405556 created "2020-09-01" @default.
- W3080405556 creator A5029169901 @default.
- W3080405556 creator A5040751355 @default.
- W3080405556 creator A5066077721 @default.
- W3080405556 creator A5070293380 @default.
- W3080405556 date "2020-01-01" @default.
- W3080405556 modified "2023-09-27" @default.
- W3080405556 title "Evaluating Explanation Methods for Deep Learning in Computer Security" @default.
- W3080405556 hasPublicationYear "2020" @default.
- W3080405556 type Work @default.
- W3080405556 sameAs 3080405556 @default.
- W3080405556 citedByCount "1" @default.
- W3080405556 countsByYear W30804055562023 @default.
- W3080405556 crossrefType "proceedings-article" @default.
- W3080405556 hasAuthorship W3080405556A5029169901 @default.
- W3080405556 hasAuthorship W3080405556A5040751355 @default.
- W3080405556 hasAuthorship W3080405556A5066077721 @default.
- W3080405556 hasAuthorship W3080405556A5070293380 @default.
- W3080405556 hasConcept C104317684 @default.
- W3080405556 hasConcept C108583219 @default.
- W3080405556 hasConcept C119857082 @default.
- W3080405556 hasConcept C121822524 @default.
- W3080405556 hasConcept C127413603 @default.
- W3080405556 hasConcept C151730666 @default.
- W3080405556 hasConcept C154945302 @default.
- W3080405556 hasConcept C185592680 @default.
- W3080405556 hasConcept C2779343474 @default.
- W3080405556 hasConcept C2780428219 @default.
- W3080405556 hasConcept C38652104 @default.
- W3080405556 hasConcept C41008148 @default.
- W3080405556 hasConcept C50644808 @default.
- W3080405556 hasConcept C541664917 @default.
- W3080405556 hasConcept C55493867 @default.
- W3080405556 hasConcept C63479239 @default.
- W3080405556 hasConcept C78519656 @default.
- W3080405556 hasConcept C86803240 @default.
- W3080405556 hasConcept C95713431 @default.
- W3080405556 hasConceptScore W3080405556C104317684 @default.
- W3080405556 hasConceptScore W3080405556C108583219 @default.
- W3080405556 hasConceptScore W3080405556C119857082 @default.
- W3080405556 hasConceptScore W3080405556C121822524 @default.
- W3080405556 hasConceptScore W3080405556C127413603 @default.
- W3080405556 hasConceptScore W3080405556C151730666 @default.
- W3080405556 hasConceptScore W3080405556C154945302 @default.
- W3080405556 hasConceptScore W3080405556C185592680 @default.
- W3080405556 hasConceptScore W3080405556C2779343474 @default.
- W3080405556 hasConceptScore W3080405556C2780428219 @default.
- W3080405556 hasConceptScore W3080405556C38652104 @default.
- W3080405556 hasConceptScore W3080405556C41008148 @default.
- W3080405556 hasConceptScore W3080405556C50644808 @default.
- W3080405556 hasConceptScore W3080405556C541664917 @default.
- W3080405556 hasConceptScore W3080405556C55493867 @default.
- W3080405556 hasConceptScore W3080405556C63479239 @default.
- W3080405556 hasConceptScore W3080405556C78519656 @default.
- W3080405556 hasConceptScore W3080405556C86803240 @default.
- W3080405556 hasConceptScore W3080405556C95713431 @default.
- W3080405556 hasLocation W30804055561 @default.
- W3080405556 hasOpenAccess W3080405556 @default.
- W3080405556 hasPrimaryLocation W30804055561 @default.
- W3080405556 hasRelatedWork W1982736558 @default.
- W3080405556 hasRelatedWork W2088086019 @default.
- W3080405556 hasRelatedWork W2472016386 @default.
- W3080405556 hasRelatedWork W2572100142 @default.
- W3080405556 hasRelatedWork W2763172566 @default.
- W3080405556 hasRelatedWork W2798151756 @default.
- W3080405556 hasRelatedWork W2807015674 @default.
- W3080405556 hasRelatedWork W2910705748 @default.
- W3080405556 hasRelatedWork W2914598080 @default.
- W3080405556 hasRelatedWork W2956993847 @default.
- W3080405556 hasRelatedWork W2964303497 @default.
- W3080405556 hasRelatedWork W3000471247 @default.
- W3080405556 hasRelatedWork W3005940936 @default.
- W3080405556 hasRelatedWork W3094613840 @default.
- W3080405556 hasRelatedWork W3097867666 @default.
- W3080405556 hasRelatedWork W3118763591 @default.
- W3080405556 hasRelatedWork W3120397982 @default.
- W3080405556 hasRelatedWork W3132191748 @default.
- W3080405556 hasRelatedWork W3154328634 @default.
- W3080405556 hasRelatedWork W3207938806 @default.
- W3080405556 isParatext "false" @default.
- W3080405556 isRetracted "false" @default.
- W3080405556 magId "3080405556" @default.
- W3080405556 workType "article" @default.