Matches in SemOpenAlex for { <https://semopenalex.org/work/W2971196104> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W2971196104 startingPage "462" @default.
- W2971196104 abstract "One of the tasks in the 2017 iDASH secure genome analysis competition was to enable training of logistic regression models over encrypted genomic data. More precisely, given a list of approximately 1500 patient records, each with 18 binary features containing information on specific mutations, the idea was for the data holder to encrypt the records using homomorphic encryption, and send them to an untrusted cloud for storage. The cloud could then homomorphically apply a training algorithm on the encrypted data to obtain an encrypted logistic regression model, which can be sent to the data holder for decryption. In this way, the data holder could successfully outsource the training process without revealing either her sensitive data, or the trained model, to the cloud. Our solution to this problem has several novelties: we use a multi-bit plaintext space in fully homomorphic encryption together with fixed point number encoding; we combine bootstrapping in fully homomorphic encryption with a scaling operation in fixed point arithmetic; we use a minimax polynomial approximation to the sigmoid function and the 1-bit gradient descent method to reduce the plaintext growth in the training process. Our algorithm for training over encrypted data takes 0.4–3.2 hours per iteration of gradient descent. We demonstrate the feasibility but high computational cost of training over encrypted data. On the other hand, our method can guarantee the highest level of data privacy in critical applications." @default.
- W2971196104 created "2019-09-05" @default.
- W2971196104 creator A5002850656 @default.
- W2971196104 creator A5012602812 @default.
- W2971196104 creator A5022499603 @default.
- W2971196104 creator A5036797884 @default.
- W2971196104 creator A5056649868 @default.
- W2971196104 creator A5063170074 @default.
- W2971196104 creator A5077373938 @default.
- W2971196104 date "2018-01-01" @default.
- W2971196104 modified "2023-09-30" @default.
- W2971196104 title "Logistic regression over encrypted data from fully homomorphic encryption." @default.
- W2971196104 hasPublicationYear "2018" @default.
- W2971196104 type Work @default.
- W2971196104 sameAs 2971196104 @default.
- W2971196104 citedByCount "1" @default.
- W2971196104 countsByYear W29711961042019 @default.
- W2971196104 crossrefType "posted-content" @default.
- W2971196104 hasAuthorship W2971196104A5002850656 @default.
- W2971196104 hasAuthorship W2971196104A5012602812 @default.
- W2971196104 hasAuthorship W2971196104A5022499603 @default.
- W2971196104 hasAuthorship W2971196104A5036797884 @default.
- W2971196104 hasAuthorship W2971196104A5056649868 @default.
- W2971196104 hasAuthorship W2971196104A5063170074 @default.
- W2971196104 hasAuthorship W2971196104A5077373938 @default.
- W2971196104 hasConcept C11413529 @default.
- W2971196104 hasConcept C124101348 @default.
- W2971196104 hasConcept C148730421 @default.
- W2971196104 hasConcept C158338273 @default.
- W2971196104 hasConcept C38652104 @default.
- W2971196104 hasConcept C41008148 @default.
- W2971196104 hasConcept C80444323 @default.
- W2971196104 hasConcept C92717368 @default.
- W2971196104 hasConceptScore W2971196104C11413529 @default.
- W2971196104 hasConceptScore W2971196104C124101348 @default.
- W2971196104 hasConceptScore W2971196104C148730421 @default.
- W2971196104 hasConceptScore W2971196104C158338273 @default.
- W2971196104 hasConceptScore W2971196104C38652104 @default.
- W2971196104 hasConceptScore W2971196104C41008148 @default.
- W2971196104 hasConceptScore W2971196104C80444323 @default.
- W2971196104 hasConceptScore W2971196104C92717368 @default.
- W2971196104 hasLocation W29711961041 @default.
- W2971196104 hasOpenAccess W2971196104 @default.
- W2971196104 hasPrimaryLocation W29711961041 @default.
- W2971196104 hasRelatedWork W2154496743 @default.
- W2971196104 hasRelatedWork W2188601887 @default.
- W2971196104 hasRelatedWork W2495314241 @default.
- W2971196104 hasRelatedWork W2578401585 @default.
- W2971196104 hasRelatedWork W2595862006 @default.
- W2971196104 hasRelatedWork W2626640171 @default.
- W2971196104 hasRelatedWork W2760163263 @default.
- W2971196104 hasRelatedWork W2902602862 @default.
- W2971196104 hasRelatedWork W2904455524 @default.
- W2971196104 hasRelatedWork W2950585479 @default.
- W2971196104 hasRelatedWork W2982485243 @default.
- W2971196104 hasRelatedWork W3012309368 @default.
- W2971196104 hasRelatedWork W3021663773 @default.
- W2971196104 hasRelatedWork W2507991566 @default.
- W2971196104 hasRelatedWork W2877598332 @default.
- W2971196104 hasRelatedWork W2930651283 @default.
- W2971196104 hasRelatedWork W2931316022 @default.
- W2971196104 hasRelatedWork W3039144899 @default.
- W2971196104 hasRelatedWork W3138350009 @default.
- W2971196104 hasRelatedWork W3180948800 @default.
- W2971196104 hasVolume "2018" @default.
- W2971196104 isParatext "false" @default.
- W2971196104 isRetracted "false" @default.
- W2971196104 magId "2971196104" @default.
- W2971196104 workType "article" @default.