FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2969795212> ?p ?o ?g. }

• W2969795212 abstract "Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. In this paper, we present MODEF, a cross-layer model diversity ensemble framework. MODEF intelligently combines unsupervised model denoising ensemble with supervised model verification ensemble by quantifying model diversity, aiming to boost the robustness of the target model against adversarial examples. Evaluated using eleven representative attacks on popular benchmark datasets, we show that MODEF achieves remarkable defense success rates, compared with existing defense methods, and provides a superior capability of repairing adversarial inputs and making correct predictions with high accuracy in the presence of black-box attacks." @default.
• W2969795212 created "2019-08-29" @default.
• W2969795212 creator A5017360203 @default.
• W2969795212 creator A5028240524 @default.
• W2969795212 creator A5060093535 @default.
• W2969795212 creator A5069331320 @default.
• W2969795212 date "2019-08-20" @default.
• W2969795212 modified "2023-09-27" @default.
• W2969795212 title "Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks" @default.
• W2969795212 cites W1019462315 @default.
• W2969795212 cites W1821462560 @default.
• W2969795212 cites W1883420340 @default.
• W2969795212 cites W1966976587 @default.
• W2969795212 cites W1983320747 @default.
• W2969795212 cites W2025768430 @default.
• W2969795212 cites W2135184018 @default.
• W2969795212 cites W2145094598 @default.
• W2969795212 cites W2146337213 @default.
• W2969795212 cites W2151503710 @default.
• W2969795212 cites W2163605009 @default.
• W2969795212 cites W2180612164 @default.
• W2969795212 cites W2243397390 @default.
• W2969795212 cites W2331128040 @default.
• W2969795212 cites W2408141691 @default.
• W2969795212 cites W2460937040 @default.
• W2969795212 cites W2590523583 @default.
• W2969795212 cites W2603766943 @default.
• W2969795212 cites W2612983688 @default.
• W2969795212 cites W2614634292 @default.
• W2969795212 cites W2618043096 @default.
• W2969795212 cites W2759358869 @default.
• W2969795212 cites W2774018344 @default.
• W2969795212 cites W2783692467 @default.
• W2969795212 cites W2810080315 @default.
• W2969795212 cites W2950468330 @default.
• W2969795212 cites W2963001136 @default.
• W2969795212 cites W2963207607 @default.
• W2969795212 cites W2963446712 @default.
• W2969795212 cites W2963612069 @default.
• W2969795212 cites W2963744840 @default.
• W2969795212 cites W2963857521 @default.
• W2969795212 cites W2963895533 @default.
• W2969795212 cites W2964082701 @default.
• W2969795212 cites W2964153729 @default.
• W2969795212 cites W2964197269 @default.
• W2969795212 cites W2964253222 @default.
• W2969795212 doi "https://doi.org/10.48550/arxiv.1908.07667" @default.
• W2969795212 hasPublicationYear "2019" @default.
• W2969795212 type Work @default.
• W2969795212 sameAs 2969795212 @default.
• W2969795212 citedByCount "0" @default.
• W2969795212 crossrefType "posted-content" @default.
• W2969795212 hasAuthorship W2969795212A5017360203 @default.
• W2969795212 hasAuthorship W2969795212A5028240524 @default.
• W2969795212 hasAuthorship W2969795212A5060093535 @default.
• W2969795212 hasAuthorship W2969795212A5069331320 @default.
• W2969795212 hasBestOaLocation W29697952121 @default.
• W2969795212 hasConcept C104317684 @default.
• W2969795212 hasConcept C119857082 @default.
• W2969795212 hasConcept C119898033 @default.
• W2969795212 hasConcept C13280743 @default.
• W2969795212 hasConcept C153180895 @default.
• W2969795212 hasConcept C154945302 @default.
• W2969795212 hasConcept C185592680 @default.
• W2969795212 hasConcept C185798385 @default.
• W2969795212 hasConcept C205649164 @default.
• W2969795212 hasConcept C2984842247 @default.
• W2969795212 hasConcept C37736160 @default.
• W2969795212 hasConcept C41008148 @default.
• W2969795212 hasConcept C45942800 @default.
• W2969795212 hasConcept C50644808 @default.
• W2969795212 hasConcept C55493867 @default.
• W2969795212 hasConcept C63479239 @default.
• W2969795212 hasConcept C94966114 @default.
• W2969795212 hasConceptScore W2969795212C104317684 @default.
• W2969795212 hasConceptScore W2969795212C119857082 @default.
• W2969795212 hasConceptScore W2969795212C119898033 @default.
• W2969795212 hasConceptScore W2969795212C13280743 @default.
• W2969795212 hasConceptScore W2969795212C153180895 @default.
• W2969795212 hasConceptScore W2969795212C154945302 @default.
• W2969795212 hasConceptScore W2969795212C185592680 @default.
• W2969795212 hasConceptScore W2969795212C185798385 @default.
• W2969795212 hasConceptScore W2969795212C205649164 @default.
• W2969795212 hasConceptScore W2969795212C2984842247 @default.
• W2969795212 hasConceptScore W2969795212C37736160 @default.
• W2969795212 hasConceptScore W2969795212C41008148 @default.
• W2969795212 hasConceptScore W2969795212C45942800 @default.
• W2969795212 hasConceptScore W2969795212C50644808 @default.
• W2969795212 hasConceptScore W2969795212C55493867 @default.
• W2969795212 hasConceptScore W2969795212C63479239 @default.
• W2969795212 hasConceptScore W2969795212C94966114 @default.
• W2969795212 hasLocation W29697952121 @default.
• W2969795212 hasOpenAccess W2969795212 @default.
• W2969795212 hasPrimaryLocation W29697952121 @default.
• W2969795212 hasRelatedWork W2952919291 @default.
• W2969795212 hasRelatedWork W2963857521 @default.
• W2969795212 hasRelatedWork W2969795212 @default.
• W2969795212 hasRelatedWork W3017431885 @default.
• W2969795212 hasRelatedWork W3021867388 @default.
• W2969795212 hasRelatedWork W3026118066 @default.

• next