Matches in SemOpenAlex for { <https://semopenalex.org/work/W2895782209> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2895782209 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.
- W2895782209 created "2018-10-26" @default.
- W2895782209 creator A5002850656 @default.
- W2895782209 creator A5012602812 @default.
- W2895782209 creator A5022499603 @default.
- W2895782209 creator A5036797884 @default.
- W2895782209 creator A5056649868 @default.
- W2895782209 creator A5063170074 @default.
- W2895782209 creator A5077373938 @default.
- W2895782209 date "2018-10-01" @default.
- W2895782209 modified "2023-10-02" @default.
- W2895782209 title "Logistic regression over encrypted data from fully homomorphic encryption" @default.
- W2895782209 cites W1974434931 @default.
- W2895782209 cites W2164327070 @default.
- W2895782209 cites W2407022425 @default.
- W2895782209 doi "https://doi.org/10.1186/s12920-018-0397-z" @default.
- W2895782209 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/6180402" @default.
- W2895782209 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30309350" @default.
- W2895782209 hasPublicationYear "2018" @default.
- W2895782209 type Work @default.
- W2895782209 sameAs 2895782209 @default.
- W2895782209 citedByCount "66" @default.
- W2895782209 countsByYear W28957822092018 @default.
- W2895782209 countsByYear W28957822092019 @default.
- W2895782209 countsByYear W28957822092020 @default.
- W2895782209 countsByYear W28957822092021 @default.
- W2895782209 countsByYear W28957822092022 @default.
- W2895782209 countsByYear W28957822092023 @default.
- W2895782209 crossrefType "journal-article" @default.
- W2895782209 hasAuthorship W2895782209A5002850656 @default.
- W2895782209 hasAuthorship W2895782209A5012602812 @default.
- W2895782209 hasAuthorship W2895782209A5022499603 @default.
- W2895782209 hasAuthorship W2895782209A5036797884 @default.
- W2895782209 hasAuthorship W2895782209A5056649868 @default.
- W2895782209 hasAuthorship W2895782209A5063170074 @default.
- W2895782209 hasAuthorship W2895782209A5077373938 @default.
- W2895782209 hasBestOaLocation W28957822091 @default.
- W2895782209 hasConcept C11413529 @default.
- W2895782209 hasConcept C124101348 @default.
- W2895782209 hasConcept C148730421 @default.
- W2895782209 hasConcept C157553263 @default.
- W2895782209 hasConcept C158338273 @default.
- W2895782209 hasConcept C38652104 @default.
- W2895782209 hasConcept C41008148 @default.
- W2895782209 hasConcept C80444323 @default.
- W2895782209 hasConcept C92717368 @default.
- W2895782209 hasConceptScore W2895782209C11413529 @default.
- W2895782209 hasConceptScore W2895782209C124101348 @default.
- W2895782209 hasConceptScore W2895782209C148730421 @default.
- W2895782209 hasConceptScore W2895782209C157553263 @default.
- W2895782209 hasConceptScore W2895782209C158338273 @default.
- W2895782209 hasConceptScore W2895782209C38652104 @default.
- W2895782209 hasConceptScore W2895782209C41008148 @default.
- W2895782209 hasConceptScore W2895782209C80444323 @default.
- W2895782209 hasConceptScore W2895782209C92717368 @default.
- W2895782209 hasIssue "S4" @default.
- W2895782209 hasLocation W28957822091 @default.
- W2895782209 hasLocation W28957822092 @default.
- W2895782209 hasLocation W28957822093 @default.
- W2895782209 hasLocation W28957822094 @default.
- W2895782209 hasLocation W28957822095 @default.
- W2895782209 hasLocation W28957822096 @default.
- W2895782209 hasLocation W28957822097 @default.
- W2895782209 hasOpenAccess W2895782209 @default.
- W2895782209 hasPrimaryLocation W28957822091 @default.
- W2895782209 hasRelatedWork W2089468229 @default.
- W2895782209 hasRelatedWork W2340393497 @default.
- W2895782209 hasRelatedWork W2384710392 @default.
- W2895782209 hasRelatedWork W2895782209 @default.
- W2895782209 hasRelatedWork W2962728853 @default.
- W2895782209 hasRelatedWork W2969350772 @default.
- W2895782209 hasRelatedWork W3023042109 @default.
- W2895782209 hasRelatedWork W3082612542 @default.
- W2895782209 hasRelatedWork W3119182752 @default.
- W2895782209 hasRelatedWork W4386474178 @default.
- W2895782209 hasVolume "11" @default.
- W2895782209 isParatext "false" @default.
- W2895782209 isRetracted "false" @default.
- W2895782209 magId "2895782209" @default.
- W2895782209 workType "article" @default.