Matches in SemOpenAlex for { <https://semopenalex.org/work/W4315706064> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4315706064 endingPage "342" @default.
- W4315706064 startingPage "325" @default.
- W4315706064 abstract "Privacy-preserving solutions enable companies to offload confidential data to third-party services while fulfilling their government regulations. To accomplish this, they leverage various cryptographic techniques such as Homomorphic Encryption (HE), which allows performing computation on encrypted data. Most HE schemes work in a SIMD fashion, and the data packing method can dramatically affect the running time and memory costs. Finding a packing method that leads to an optimal performant implementation is a hard task. We present a simple and intuitive framework that abstracts the packing decision for the user. We explain its underlying data structures and optimizer, and propose a novel algorithm for performing 2D convolution operations. We used this framework to implement an HE-friendly version of AlexNet, which runs in three minutes, several orders of magnitude faster than other state-of-the-art solutions that only use HE." @default.
- W4315706064 created "2023-01-12" @default.
- W4315706064 creator A5007886066 @default.
- W4315706064 creator A5012664780 @default.
- W4315706064 creator A5014058894 @default.
- W4315706064 creator A5023713634 @default.
- W4315706064 creator A5026541410 @default.
- W4315706064 creator A5027308449 @default.
- W4315706064 creator A5031760144 @default.
- W4315706064 creator A5037270145 @default.
- W4315706064 creator A5050045238 @default.
- W4315706064 creator A5051431512 @default.
- W4315706064 creator A5072874959 @default.
- W4315706064 creator A5087060990 @default.
- W4315706064 date "2023-01-01" @default.
- W4315706064 modified "2023-09-30" @default.
- W4315706064 title "HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data" @default.
- W4315706064 doi "https://doi.org/10.56553/popets-2023-0020" @default.
- W4315706064 hasPublicationYear "2023" @default.
- W4315706064 type Work @default.
- W4315706064 citedByCount "1" @default.
- W4315706064 countsByYear W43157060642023 @default.
- W4315706064 crossrefType "journal-article" @default.
- W4315706064 hasAuthorship W4315706064A5007886066 @default.
- W4315706064 hasAuthorship W4315706064A5012664780 @default.
- W4315706064 hasAuthorship W4315706064A5014058894 @default.
- W4315706064 hasAuthorship W4315706064A5023713634 @default.
- W4315706064 hasAuthorship W4315706064A5026541410 @default.
- W4315706064 hasAuthorship W4315706064A5027308449 @default.
- W4315706064 hasAuthorship W4315706064A5031760144 @default.
- W4315706064 hasAuthorship W4315706064A5037270145 @default.
- W4315706064 hasAuthorship W4315706064A5050045238 @default.
- W4315706064 hasAuthorship W4315706064A5051431512 @default.
- W4315706064 hasAuthorship W4315706064A5072874959 @default.
- W4315706064 hasAuthorship W4315706064A5087060990 @default.
- W4315706064 hasBestOaLocation W43157060641 @default.
- W4315706064 hasConcept C11413529 @default.
- W4315706064 hasConcept C120314980 @default.
- W4315706064 hasConcept C148730421 @default.
- W4315706064 hasConcept C153083717 @default.
- W4315706064 hasConcept C154945302 @default.
- W4315706064 hasConcept C158338273 @default.
- W4315706064 hasConcept C178489894 @default.
- W4315706064 hasConcept C38652104 @default.
- W4315706064 hasConcept C41008148 @default.
- W4315706064 hasConcept C45374587 @default.
- W4315706064 hasConcept C80444323 @default.
- W4315706064 hasConceptScore W4315706064C11413529 @default.
- W4315706064 hasConceptScore W4315706064C120314980 @default.
- W4315706064 hasConceptScore W4315706064C148730421 @default.
- W4315706064 hasConceptScore W4315706064C153083717 @default.
- W4315706064 hasConceptScore W4315706064C154945302 @default.
- W4315706064 hasConceptScore W4315706064C158338273 @default.
- W4315706064 hasConceptScore W4315706064C178489894 @default.
- W4315706064 hasConceptScore W4315706064C38652104 @default.
- W4315706064 hasConceptScore W4315706064C41008148 @default.
- W4315706064 hasConceptScore W4315706064C45374587 @default.
- W4315706064 hasConceptScore W4315706064C80444323 @default.
- W4315706064 hasIssue "1" @default.
- W4315706064 hasLocation W43157060641 @default.
- W4315706064 hasLocation W43157060642 @default.
- W4315706064 hasLocation W43157060643 @default.
- W4315706064 hasOpenAccess W4315706064 @default.
- W4315706064 hasPrimaryLocation W43157060641 @default.
- W4315706064 hasRelatedWork W1623766202 @default.
- W4315706064 hasRelatedWork W2037113620 @default.
- W4315706064 hasRelatedWork W2340393497 @default.
- W4315706064 hasRelatedWork W2395982605 @default.
- W4315706064 hasRelatedWork W2765100738 @default.
- W4315706064 hasRelatedWork W2949060133 @default.
- W4315706064 hasRelatedWork W2970980997 @default.
- W4315706064 hasRelatedWork W3022075301 @default.
- W4315706064 hasRelatedWork W3028834223 @default.
- W4315706064 hasRelatedWork W4313124477 @default.
- W4315706064 hasVolume "2023" @default.
- W4315706064 isParatext "false" @default.
- W4315706064 isRetracted "false" @default.
- W4315706064 workType "article" @default.