Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892587850> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2892587850 abstract "Privacy recently emerges as a severe concern in deep learning, that is, sensitive data must be prohibited from being shared with the third party during deep neural network development. In this paper, we propose Morphed Learning (MoLe), an efficient and secure scheme to deliver deep learning data. MoLe has two main components: data morphing and Augmented Convolutional (Aug-Conv) layer. Data morphing allows data providers to send morphed data without privacy information, while Aug-Conv layer helps deep learning developers to apply their networks on the morphed data without performance penalty. MoLe provides stronger security while introducing lower overhead compared to GAZELLE (USENIX Security 2018), which is another method with no performance penalty on the neural network. When using MoLe for VGG-16 network on CIFAR dataset, the computational overhead is only 9% and the data transmission overhead is 5.12%. As a comparison, GAZELLE has computational overhead of 10,000 times and data transmission overhead of 421,000 times. In this setting, the attack success rate of adversary is 7.9 x 10^{-90} for MoLe and 2.9 x 10^{-30} for GAZELLE, respectively." @default.
- W2892587850 created "2018-10-05" @default.
- W2892587850 creator A5058073627 @default.
- W2892587850 creator A5060410494 @default.
- W2892587850 creator A5062298445 @default.
- W2892587850 creator A5069190300 @default.
- W2892587850 date "2018-09-20" @default.
- W2892587850 modified "2023-09-24" @default.
- W2892587850 title "Morphed Learning: Towards Privacy-Preserving for Deep Learning Based Applications" @default.
- W2892587850 hasPublicationYear "2018" @default.
- W2892587850 type Work @default.
- W2892587850 sameAs 2892587850 @default.
- W2892587850 citedByCount "0" @default.
- W2892587850 crossrefType "posted-content" @default.
- W2892587850 hasAuthorship W2892587850A5058073627 @default.
- W2892587850 hasAuthorship W2892587850A5060410494 @default.
- W2892587850 hasAuthorship W2892587850A5062298445 @default.
- W2892587850 hasAuthorship W2892587850A5069190300 @default.
- W2892587850 hasConcept C108583219 @default.
- W2892587850 hasConcept C111919701 @default.
- W2892587850 hasConcept C119857082 @default.
- W2892587850 hasConcept C154945302 @default.
- W2892587850 hasConcept C2779960059 @default.
- W2892587850 hasConcept C31258907 @default.
- W2892587850 hasConcept C38652104 @default.
- W2892587850 hasConcept C41008148 @default.
- W2892587850 hasConcept C41065033 @default.
- W2892587850 hasConcept C50637493 @default.
- W2892587850 hasConcept C50644808 @default.
- W2892587850 hasConcept C557945733 @default.
- W2892587850 hasConcept C761482 @default.
- W2892587850 hasConcept C76155785 @default.
- W2892587850 hasConcept C81363708 @default.
- W2892587850 hasConceptScore W2892587850C108583219 @default.
- W2892587850 hasConceptScore W2892587850C111919701 @default.
- W2892587850 hasConceptScore W2892587850C119857082 @default.
- W2892587850 hasConceptScore W2892587850C154945302 @default.
- W2892587850 hasConceptScore W2892587850C2779960059 @default.
- W2892587850 hasConceptScore W2892587850C31258907 @default.
- W2892587850 hasConceptScore W2892587850C38652104 @default.
- W2892587850 hasConceptScore W2892587850C41008148 @default.
- W2892587850 hasConceptScore W2892587850C41065033 @default.
- W2892587850 hasConceptScore W2892587850C50637493 @default.
- W2892587850 hasConceptScore W2892587850C50644808 @default.
- W2892587850 hasConceptScore W2892587850C557945733 @default.
- W2892587850 hasConceptScore W2892587850C761482 @default.
- W2892587850 hasConceptScore W2892587850C76155785 @default.
- W2892587850 hasConceptScore W2892587850C81363708 @default.
- W2892587850 hasLocation W28925878501 @default.
- W2892587850 hasOpenAccess W2892587850 @default.
- W2892587850 hasPrimaryLocation W28925878501 @default.
- W2892587850 hasRelatedWork W2137351756 @default.
- W2892587850 hasRelatedWork W2803199352 @default.
- W2892587850 hasRelatedWork W2804403287 @default.
- W2892587850 hasRelatedWork W2809964047 @default.
- W2892587850 hasRelatedWork W2904873688 @default.
- W2892587850 hasRelatedWork W2914756587 @default.
- W2892587850 hasRelatedWork W2938223462 @default.
- W2892587850 hasRelatedWork W2974852124 @default.
- W2892587850 hasRelatedWork W3001426930 @default.
- W2892587850 hasRelatedWork W3016560828 @default.
- W2892587850 hasRelatedWork W3028719682 @default.
- W2892587850 hasRelatedWork W3044222737 @default.
- W2892587850 hasRelatedWork W3084324382 @default.
- W2892587850 hasRelatedWork W3158394771 @default.
- W2892587850 hasRelatedWork W3169827479 @default.
- W2892587850 hasRelatedWork W3174155717 @default.
- W2892587850 hasRelatedWork W3209606284 @default.
- W2892587850 hasRelatedWork W2182826533 @default.
- W2892587850 hasRelatedWork W2187331692 @default.
- W2892587850 hasRelatedWork W2593523670 @default.
- W2892587850 isParatext "false" @default.
- W2892587850 isRetracted "false" @default.
- W2892587850 magId "2892587850" @default.
- W2892587850 workType "article" @default.