Matches in SemOpenAlex for { <https://semopenalex.org/work/W3108168093> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3108168093 abstract "The success of deep learning is largely due to the availability of big training data nowadays. However, data privacy could be a big concern, especially when the training or inference is done on untrusted third-party servers. Fully Homomorphic Encryption (FHE) is a powerful cryptography technique that enables computation on encrypted data in the absence of decryption key, thus could protect data privacy in an outsourced computation environment. However, due to its large performance and resource overheads, current applications of FHE to deep learning are still limited to very simple tasks. In this paper, we first propose a neural network training framework on FHE encrypted data, namely PrivGD. PrivGD leverages the Single-Instruction Multiple-Data (SIMD) packing feature of FHE to efficiently implement the Gradient Descent algorithm in the encrypted domain. In particular, PrivGD is the first to support training a multi-class classification network with double-precision float-point weights through approximated Softmax function in FHE, which has never been done before to the best of our knowledge. Then, we show how to apply FHE with transfer learning for more complicated real-world applications. We consider outsourced diagnosis services, as with the Machine-Learning-as-a-Service paradigm, for multi-class machine faults on machine sensor datasets under different operating conditions. As directly applying the source model trained on the source dataset (collected from source operating condition) to the target dataset (collect from the target operating condition) will lead to degraded diagnosis accuracy, we propose to transfer the source model to the target domain by retraining (fine-tuning) the classifier of the source model with data from the target domain. The target domain data is encrypted with FHE so that its privacy is preserved during the transfer learning process. We implement the secure transfer learning process with our PrivGD framework. Experiments results show that by fine-tuning a source model for fewer than 10 epochs with encrypted target domain data, the model can converge to an increased diagnosis accuracy by up to 20%, while the whole fine-tuning process takes approximate 3.85 h on our commodity server." @default.
- W3108168093 created "2020-12-07" @default.
- W3108168093 creator A5030466993 @default.
- W3108168093 creator A5058648309 @default.
- W3108168093 creator A5074344378 @default.
- W3108168093 date "2020-01-01" @default.
- W3108168093 modified "2023-09-23" @default.
- W3108168093 title "Secure Transfer Learning for Machine Fault Diagnosis Under Different Operating Conditions" @default.
- W3108168093 cites W1494049356 @default.
- W3108168093 cites W1966731635 @default.
- W3108168093 cites W2023745373 @default.
- W3108168093 cites W2027471022 @default.
- W3108168093 cites W2031533839 @default.
- W3108168093 cites W2037668591 @default.
- W3108168093 cites W2088492763 @default.
- W3108168093 cites W2165698076 @default.
- W3108168093 cites W2177209050 @default.
- W3108168093 cites W2321342612 @default.
- W3108168093 cites W236632755 @default.
- W3108168093 cites W2567698949 @default.
- W3108168093 cites W2701059868 @default.
- W3108168093 cites W2765200655 @default.
- W3108168093 cites W2766225332 @default.
- W3108168093 cites W2768174108 @default.
- W3108168093 cites W2794888826 @default.
- W3108168093 cites W2801958627 @default.
- W3108168093 cites W2889746123 @default.
- W3108168093 cites W2896938420 @default.
- W3108168093 cites W2973877675 @default.
- W3108168093 cites W3003532255 @default.
- W3108168093 cites W4243202529 @default.
- W3108168093 doi "https://doi.org/10.1007/978-3-030-62576-4_14" @default.
- W3108168093 hasPublicationYear "2020" @default.
- W3108168093 type Work @default.
- W3108168093 sameAs 3108168093 @default.
- W3108168093 citedByCount "0" @default.
- W3108168093 crossrefType "book-chapter" @default.
- W3108168093 hasAuthorship W3108168093A5030466993 @default.
- W3108168093 hasAuthorship W3108168093A5058648309 @default.
- W3108168093 hasAuthorship W3108168093A5074344378 @default.
- W3108168093 hasConcept C108583219 @default.
- W3108168093 hasConcept C119857082 @default.
- W3108168093 hasConcept C124101348 @default.
- W3108168093 hasConcept C148730421 @default.
- W3108168093 hasConcept C150899416 @default.
- W3108168093 hasConcept C154945302 @default.
- W3108168093 hasConcept C158338273 @default.
- W3108168093 hasConcept C188441871 @default.
- W3108168093 hasConcept C206688291 @default.
- W3108168093 hasConcept C31258907 @default.
- W3108168093 hasConcept C41008148 @default.
- W3108168093 hasConcept C50644808 @default.
- W3108168093 hasConcept C93996380 @default.
- W3108168093 hasConceptScore W3108168093C108583219 @default.
- W3108168093 hasConceptScore W3108168093C119857082 @default.
- W3108168093 hasConceptScore W3108168093C124101348 @default.
- W3108168093 hasConceptScore W3108168093C148730421 @default.
- W3108168093 hasConceptScore W3108168093C150899416 @default.
- W3108168093 hasConceptScore W3108168093C154945302 @default.
- W3108168093 hasConceptScore W3108168093C158338273 @default.
- W3108168093 hasConceptScore W3108168093C188441871 @default.
- W3108168093 hasConceptScore W3108168093C206688291 @default.
- W3108168093 hasConceptScore W3108168093C31258907 @default.
- W3108168093 hasConceptScore W3108168093C41008148 @default.
- W3108168093 hasConceptScore W3108168093C50644808 @default.
- W3108168093 hasConceptScore W3108168093C93996380 @default.
- W3108168093 hasLocation W31081680931 @default.
- W3108168093 hasOpenAccess W3108168093 @default.
- W3108168093 hasPrimaryLocation W31081680931 @default.
- W3108168093 hasRelatedWork W10202958 @default.
- W3108168093 hasRelatedWork W10944326 @default.
- W3108168093 hasRelatedWork W1152574 @default.
- W3108168093 hasRelatedWork W11816003 @default.
- W3108168093 hasRelatedWork W12016155 @default.
- W3108168093 hasRelatedWork W13538861 @default.
- W3108168093 hasRelatedWork W6908809 @default.
- W3108168093 hasRelatedWork W7303821 @default.
- W3108168093 hasRelatedWork W9190101 @default.
- W3108168093 hasRelatedWork W929682 @default.
- W3108168093 isParatext "false" @default.
- W3108168093 isRetracted "false" @default.
- W3108168093 magId "3108168093" @default.
- W3108168093 workType "book-chapter" @default.