Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979776310> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W2979776310 abstract "The success of neural networks across most machine learning tasks and the persistence of adversarial examples have made the verification of such models an important quest. Several techniques have been successfully developed to verify robustness, and are now able to evaluate neural networks with thousands of nodes. The main weakness of this approach is in the specification: robustness is asserted on a validation set consisting of a finite set of examples, i.e. locally. We propose a notion of global robustness based on generative models, which asserts the robustness on a very large and representative set of examples. We show how this can be used for verifying neural networks. In this paper we experimentally explore the merits of this approach, and show how it can be used to construct realistic adversarial examples." @default.
- W2979776310 created "2019-10-18" @default.
- W2979776310 creator A5022821778 @default.
- W2979776310 creator A5071123608 @default.
- W2979776310 date "2019-12-05" @default.
- W2979776310 modified "2023-09-25" @default.
- W2979776310 title "Verification of Neural Networks: Specifying Global Robustness using Generative Models" @default.
- W2979776310 cites W2141125852 @default.
- W2979776310 cites W2543296129 @default.
- W2979776310 cites W2590796488 @default.
- W2979776310 cites W2594877703 @default.
- W2979776310 cites W2803850896 @default.
- W2979776310 cites W2892430965 @default.
- W2979776310 cites W2964253222 @default.
- W2979776310 hasPublicationYear "2019" @default.
- W2979776310 type Work @default.
- W2979776310 sameAs 2979776310 @default.
- W2979776310 citedByCount "1" @default.
- W2979776310 countsByYear W29797763102020 @default.
- W2979776310 crossrefType "posted-content" @default.
- W2979776310 hasAuthorship W2979776310A5022821778 @default.
- W2979776310 hasAuthorship W2979776310A5071123608 @default.
- W2979776310 hasConcept C104317684 @default.
- W2979776310 hasConcept C154945302 @default.
- W2979776310 hasConcept C185592680 @default.
- W2979776310 hasConcept C39890363 @default.
- W2979776310 hasConcept C41008148 @default.
- W2979776310 hasConcept C50644808 @default.
- W2979776310 hasConcept C55493867 @default.
- W2979776310 hasConcept C63479239 @default.
- W2979776310 hasConceptScore W2979776310C104317684 @default.
- W2979776310 hasConceptScore W2979776310C154945302 @default.
- W2979776310 hasConceptScore W2979776310C185592680 @default.
- W2979776310 hasConceptScore W2979776310C39890363 @default.
- W2979776310 hasConceptScore W2979776310C41008148 @default.
- W2979776310 hasConceptScore W2979776310C50644808 @default.
- W2979776310 hasConceptScore W2979776310C55493867 @default.
- W2979776310 hasConceptScore W2979776310C63479239 @default.
- W2979776310 hasLocation W29797763101 @default.
- W2979776310 hasOpenAccess W2979776310 @default.
- W2979776310 hasPrimaryLocation W29797763101 @default.
- W2979776310 hasRelatedWork W2035976912 @default.
- W2979776310 hasRelatedWork W2122478253 @default.
- W2979776310 hasRelatedWork W2141907153 @default.
- W2979776310 hasRelatedWork W2363475415 @default.
- W2979776310 hasRelatedWork W2386387936 @default.
- W2979776310 hasRelatedWork W2541791370 @default.
- W2979776310 hasRelatedWork W2810045178 @default.
- W2979776310 hasRelatedWork W3156291593 @default.
- W2979776310 hasRelatedWork W3164116745 @default.
- W2979776310 hasRelatedWork W3213778687 @default.
- W2979776310 isParatext "false" @default.
- W2979776310 isRetracted "false" @default.
- W2979776310 magId "2979776310" @default.
- W2979776310 workType "article" @default.