Matches in SemOpenAlex for { <https://semopenalex.org/work/W2989772244> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2989772244 endingPage "224" @default.
- W2989772244 startingPage "215" @default.
- W2989772244 abstract "Deep neural network (DNN) learning has witnessed significant applications in various fields, especially for prediction and classification. Frequently, the data used for training are provided by crowdsourcing workers, and the training process may violate their privacy. A qualified prediction model should protect the data privacy in training and classification/prediction phases. To address this issue, we develop a differential privacy (DP)-enabled DNN learning framework, DNN-DP, that intentionally injects noise to the affine transformation of the input data features and provides DP protection for the crowdsourced sensitive training data. Specifically, we correspondingly estimate the importance of each feature related to target categories and follow the principle that less noise is injected into the more important feature to ensure the data utility of the model. Moreover, we design an adaptive coefficient for the added noise to accommodate the heterogeneous feature value ranges. Theoretical analysis proves that DNN-DP preserves ${varepsilon }$ -differentially private in the computation. Moreover, the simulation based on the US Census data set demonstrates the superiority of our method in predictive accuracy compared with other existing privacy-aware machine learning methods." @default.
- W2989772244 created "2019-12-05" @default.
- W2989772244 creator A5024436877 @default.
- W2989772244 creator A5031234889 @default.
- W2989772244 creator A5061363755 @default.
- W2989772244 creator A5072090074 @default.
- W2989772244 date "2020-02-01" @default.
- W2989772244 modified "2023-10-10" @default.
- W2989772244 title "DNN-DP: Differential Privacy Enabled Deep Neural Network Learning Framework for Sensitive Crowdsourcing Data" @default.
- W2989772244 cites W1498436455 @default.
- W2989772244 cites W1677182931 @default.
- W2989772244 cites W2007779652 @default.
- W2989772244 cites W2051267297 @default.
- W2989772244 cites W2053637704 @default.
- W2989772244 cites W2138865266 @default.
- W2989772244 cites W2155261478 @default.
- W2989772244 cites W2162379889 @default.
- W2989772244 cites W2257979135 @default.
- W2989772244 cites W2473418344 @default.
- W2989772244 cites W2608855258 @default.
- W2989772244 cites W2748568982 @default.
- W2989772244 cites W2921140350 @default.
- W2989772244 cites W2933424288 @default.
- W2989772244 cites W2946073848 @default.
- W2989772244 cites W2963313259 @default.
- W2989772244 cites W4205228770 @default.
- W2989772244 doi "https://doi.org/10.1109/tcss.2019.2950017" @default.
- W2989772244 hasPublicationYear "2020" @default.
- W2989772244 type Work @default.
- W2989772244 sameAs 2989772244 @default.
- W2989772244 citedByCount "16" @default.
- W2989772244 countsByYear W29897722442020 @default.
- W2989772244 countsByYear W29897722442021 @default.
- W2989772244 countsByYear W29897722442022 @default.
- W2989772244 countsByYear W29897722442023 @default.
- W2989772244 crossrefType "journal-article" @default.
- W2989772244 hasAuthorship W2989772244A5024436877 @default.
- W2989772244 hasAuthorship W2989772244A5031234889 @default.
- W2989772244 hasAuthorship W2989772244A5061363755 @default.
- W2989772244 hasAuthorship W2989772244A5072090074 @default.
- W2989772244 hasConcept C108583219 @default.
- W2989772244 hasConcept C119857082 @default.
- W2989772244 hasConcept C123201435 @default.
- W2989772244 hasConcept C124101348 @default.
- W2989772244 hasConcept C136764020 @default.
- W2989772244 hasConcept C154945302 @default.
- W2989772244 hasConcept C23130292 @default.
- W2989772244 hasConcept C3017597292 @default.
- W2989772244 hasConcept C38652104 @default.
- W2989772244 hasConcept C41008148 @default.
- W2989772244 hasConcept C50644808 @default.
- W2989772244 hasConcept C62230096 @default.
- W2989772244 hasConceptScore W2989772244C108583219 @default.
- W2989772244 hasConceptScore W2989772244C119857082 @default.
- W2989772244 hasConceptScore W2989772244C123201435 @default.
- W2989772244 hasConceptScore W2989772244C124101348 @default.
- W2989772244 hasConceptScore W2989772244C136764020 @default.
- W2989772244 hasConceptScore W2989772244C154945302 @default.
- W2989772244 hasConceptScore W2989772244C23130292 @default.
- W2989772244 hasConceptScore W2989772244C3017597292 @default.
- W2989772244 hasConceptScore W2989772244C38652104 @default.
- W2989772244 hasConceptScore W2989772244C41008148 @default.
- W2989772244 hasConceptScore W2989772244C50644808 @default.
- W2989772244 hasConceptScore W2989772244C62230096 @default.
- W2989772244 hasFunder F4320327794 @default.
- W2989772244 hasIssue "1" @default.
- W2989772244 hasLocation W29897722441 @default.
- W2989772244 hasOpenAccess W2989772244 @default.
- W2989772244 hasPrimaryLocation W29897722441 @default.
- W2989772244 hasRelatedWork W2808007232 @default.
- W2989772244 hasRelatedWork W2937423831 @default.
- W2989772244 hasRelatedWork W2982556685 @default.
- W2989772244 hasRelatedWork W2982674075 @default.
- W2989772244 hasRelatedWork W3005947044 @default.
- W2989772244 hasRelatedWork W3201047814 @default.
- W2989772244 hasRelatedWork W4223943233 @default.
- W2989772244 hasRelatedWork W4225161397 @default.
- W2989772244 hasRelatedWork W4309045103 @default.
- W2989772244 hasRelatedWork W4312200629 @default.
- W2989772244 hasVolume "7" @default.
- W2989772244 isParatext "false" @default.
- W2989772244 isRetracted "false" @default.
- W2989772244 magId "2989772244" @default.
- W2989772244 workType "article" @default.