Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765200655> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2765200655 abstract "Machine learning models hosted in a cloud service are increasingly popular but risk privacy: clients sending prediction requests to the service need to disclose potentially sensitive information. In this paper, we explore the problem of privacy-preserving predictions: after each prediction, the server learns nothing about clients' input and clients learn nothing about the model. We present MiniONN, the first approach for transforming an existing neural network to an oblivious neural network supporting privacy-preserving predictions with reasonable efficiency. Unlike prior work, MiniONN requires no change to how models are trained. To this end, we design oblivious protocols for commonly used operations in neural network prediction models. We show that MiniONN outperforms existing work in terms of response latency and message sizes. We demonstrate the wide applicability of MiniONN by transforming several typical neural network models trained from standard datasets." @default.
- W2765200655 created "2017-11-10" @default.
- W2765200655 creator A5016685507 @default.
- W2765200655 creator A5022602939 @default.
- W2765200655 creator A5026907508 @default.
- W2765200655 creator A5060165452 @default.
- W2765200655 date "2017-10-30" @default.
- W2765200655 modified "2023-10-12" @default.
- W2765200655 title "Oblivious Neural Network Predictions via MiniONN Transformations" @default.
- W2765200655 cites W113737010 @default.
- W2765200655 cites W133884053 @default.
- W2765200655 cites W1577715605 @default.
- W2765200655 cites W1966731635 @default.
- W2765200655 cites W1969009977 @default.
- W2765200655 cites W1973124816 @default.
- W2765200655 cites W2027471022 @default.
- W2765200655 cites W2031738616 @default.
- W2765200655 cites W2053637704 @default.
- W2765200655 cites W2064675550 @default.
- W2765200655 cites W2083847133 @default.
- W2765200655 cites W2088492763 @default.
- W2765200655 cites W2109135024 @default.
- W2765200655 cites W2114277262 @default.
- W2765200655 cites W2132172731 @default.
- W2765200655 cites W2147768505 @default.
- W2765200655 cites W2165063012 @default.
- W2765200655 cites W2256458751 @default.
- W2765200655 cites W2398935881 @default.
- W2765200655 cites W2473418344 @default.
- W2765200655 cites W2701059868 @default.
- W2765200655 doi "https://doi.org/10.1145/3133956.3134056" @default.
- W2765200655 hasPublicationYear "2017" @default.
- W2765200655 type Work @default.
- W2765200655 sameAs 2765200655 @default.
- W2765200655 citedByCount "429" @default.
- W2765200655 countsByYear W27652006552017 @default.
- W2765200655 countsByYear W27652006552018 @default.
- W2765200655 countsByYear W27652006552019 @default.
- W2765200655 countsByYear W27652006552020 @default.
- W2765200655 countsByYear W27652006552021 @default.
- W2765200655 countsByYear W27652006552022 @default.
- W2765200655 countsByYear W27652006552023 @default.
- W2765200655 crossrefType "proceedings-article" @default.
- W2765200655 hasAuthorship W2765200655A5016685507 @default.
- W2765200655 hasAuthorship W2765200655A5022602939 @default.
- W2765200655 hasAuthorship W2765200655A5026907508 @default.
- W2765200655 hasAuthorship W2765200655A5060165452 @default.
- W2765200655 hasConcept C111919701 @default.
- W2765200655 hasConcept C119857082 @default.
- W2765200655 hasConcept C124101348 @default.
- W2765200655 hasConcept C136264566 @default.
- W2765200655 hasConcept C154945302 @default.
- W2765200655 hasConcept C162324750 @default.
- W2765200655 hasConcept C2780378061 @default.
- W2765200655 hasConcept C2984842247 @default.
- W2765200655 hasConcept C41008148 @default.
- W2765200655 hasConcept C50644808 @default.
- W2765200655 hasConcept C76155785 @default.
- W2765200655 hasConcept C79974875 @default.
- W2765200655 hasConcept C82876162 @default.
- W2765200655 hasConceptScore W2765200655C111919701 @default.
- W2765200655 hasConceptScore W2765200655C119857082 @default.
- W2765200655 hasConceptScore W2765200655C124101348 @default.
- W2765200655 hasConceptScore W2765200655C136264566 @default.
- W2765200655 hasConceptScore W2765200655C154945302 @default.
- W2765200655 hasConceptScore W2765200655C162324750 @default.
- W2765200655 hasConceptScore W2765200655C2780378061 @default.
- W2765200655 hasConceptScore W2765200655C2984842247 @default.
- W2765200655 hasConceptScore W2765200655C41008148 @default.
- W2765200655 hasConceptScore W2765200655C50644808 @default.
- W2765200655 hasConceptScore W2765200655C76155785 @default.
- W2765200655 hasConceptScore W2765200655C79974875 @default.
- W2765200655 hasConceptScore W2765200655C82876162 @default.
- W2765200655 hasFunder F4320321108 @default.
- W2765200655 hasLocation W27652006551 @default.
- W2765200655 hasOpenAccess W2765200655 @default.
- W2765200655 hasPrimaryLocation W27652006551 @default.
- W2765200655 hasRelatedWork W11765363 @default.
- W2765200655 hasRelatedWork W2376932109 @default.
- W2765200655 hasRelatedWork W2386387936 @default.
- W2765200655 hasRelatedWork W2390279801 @default.
- W2765200655 hasRelatedWork W2748952813 @default.
- W2765200655 hasRelatedWork W2899084033 @default.
- W2765200655 hasRelatedWork W3107474891 @default.
- W2765200655 hasRelatedWork W644753246 @default.
- W2765200655 hasRelatedWork W1629725936 @default.
- W2765200655 hasRelatedWork W2802349271 @default.
- W2765200655 isParatext "false" @default.
- W2765200655 isRetracted "false" @default.
- W2765200655 magId "2765200655" @default.
- W2765200655 workType "article" @default.