Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387107901> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W4387107901 endingPage "103509" @default.
- W4387107901 startingPage "103509" @default.
- W4387107901 abstract "Outsourcing Machine Learning (ML) tasks to cloud servers is a cost-effective solution when dealing with distributed data. However, outsourcing these tasks to cloud servers could lead to data breaches. Secure computing methods, such as Homomorphic Encryption (HE) and Trusted Execution Environments (TEE), have been used to protect outsourced data. Nevertheless, HE remains inefficient in processing complicated functions (e.g., non-linear functions) and TEE (e.g., Intel SGX) is not ideal for directly processing ML tasks due to side-channel attacks and parallel-unfriendly computation. In this paper, we propose a hybrid framework integrating SGX and HE, called HT2ML, to protect user's data and models. In HT2ML, HE-friendly functions are protected with HE and performed outside the enclave, while the remaining operations are performed inside the enclave obliviously. HT2ML leverages optimised HE matrix multiplications to accelerate HE computations outside the enclave while using oblivious blocks inside the enclave to prevent access-pattern-based attacks. We evaluate HT2ML using Linear Regression (LR) training and Convolutional Neural Network (CNN) inference as two instantiations. The performance results show that HT2ML is up to ∼11× faster than HE only baseline with 6-dimensional data in LR training. For CNN inference, HT2ML is ∼196× faster than the most recent approach (Xiao et al., ICDCS'21)." @default.
- W4387107901 created "2023-09-28" @default.
- W4387107901 creator A5005159928 @default.
- W4387107901 creator A5017570709 @default.
- W4387107901 creator A5055007304 @default.
- W4387107901 creator A5072470185 @default.
- W4387107901 creator A5072751099 @default.
- W4387107901 creator A5079507661 @default.
- W4387107901 date "2023-12-01" @default.
- W4387107901 modified "2023-10-09" @default.
- W4387107901 title "HT2ML: An Efficient Hybrid Framework for Privacy-preserving Machine Learning Using HE and TEE" @default.
- W4387107901 cites W1966731635 @default.
- W4387107901 cites W2108834246 @default.
- W4387107901 cites W2177209050 @default.
- W4387107901 cites W2400700555 @default.
- W4387107901 cites W3028516757 @default.
- W4387107901 cites W4206232911 @default.
- W4387107901 cites W4313855966 @default.
- W4387107901 doi "https://doi.org/10.1016/j.cose.2023.103509" @default.
- W4387107901 hasPublicationYear "2023" @default.
- W4387107901 type Work @default.
- W4387107901 citedByCount "0" @default.
- W4387107901 crossrefType "journal-article" @default.
- W4387107901 hasAuthorship W4387107901A5005159928 @default.
- W4387107901 hasAuthorship W4387107901A5017570709 @default.
- W4387107901 hasAuthorship W4387107901A5055007304 @default.
- W4387107901 hasAuthorship W4387107901A5072470185 @default.
- W4387107901 hasAuthorship W4387107901A5072751099 @default.
- W4387107901 hasAuthorship W4387107901A5079507661 @default.
- W4387107901 hasBestOaLocation W43871079011 @default.
- W4387107901 hasConcept C111919701 @default.
- W4387107901 hasConcept C113775141 @default.
- W4387107901 hasConcept C11413529 @default.
- W4387107901 hasConcept C120314980 @default.
- W4387107901 hasConcept C148730421 @default.
- W4387107901 hasConcept C154945302 @default.
- W4387107901 hasConcept C158338273 @default.
- W4387107901 hasConcept C17744445 @default.
- W4387107901 hasConcept C199539241 @default.
- W4387107901 hasConcept C2776214188 @default.
- W4387107901 hasConcept C31258907 @default.
- W4387107901 hasConcept C38652104 @default.
- W4387107901 hasConcept C41008148 @default.
- W4387107901 hasConcept C45374587 @default.
- W4387107901 hasConcept C46934059 @default.
- W4387107901 hasConcept C79974875 @default.
- W4387107901 hasConcept C81363708 @default.
- W4387107901 hasConcept C93996380 @default.
- W4387107901 hasConceptScore W4387107901C111919701 @default.
- W4387107901 hasConceptScore W4387107901C113775141 @default.
- W4387107901 hasConceptScore W4387107901C11413529 @default.
- W4387107901 hasConceptScore W4387107901C120314980 @default.
- W4387107901 hasConceptScore W4387107901C148730421 @default.
- W4387107901 hasConceptScore W4387107901C154945302 @default.
- W4387107901 hasConceptScore W4387107901C158338273 @default.
- W4387107901 hasConceptScore W4387107901C17744445 @default.
- W4387107901 hasConceptScore W4387107901C199539241 @default.
- W4387107901 hasConceptScore W4387107901C2776214188 @default.
- W4387107901 hasConceptScore W4387107901C31258907 @default.
- W4387107901 hasConceptScore W4387107901C38652104 @default.
- W4387107901 hasConceptScore W4387107901C41008148 @default.
- W4387107901 hasConceptScore W4387107901C45374587 @default.
- W4387107901 hasConceptScore W4387107901C46934059 @default.
- W4387107901 hasConceptScore W4387107901C79974875 @default.
- W4387107901 hasConceptScore W4387107901C81363708 @default.
- W4387107901 hasConceptScore W4387107901C93996380 @default.
- W4387107901 hasFunder F4320321001 @default.
- W4387107901 hasLocation W43871079011 @default.
- W4387107901 hasOpenAccess W4387107901 @default.
- W4387107901 hasPrimaryLocation W43871079011 @default.
- W4387107901 hasRelatedWork W200604156 @default.
- W4387107901 hasRelatedWork W2291845669 @default.
- W4387107901 hasRelatedWork W2325765407 @default.
- W4387107901 hasRelatedWork W2358200898 @default.
- W4387107901 hasRelatedWork W2374784346 @default.
- W4387107901 hasRelatedWork W2788012436 @default.
- W4387107901 hasRelatedWork W3125032676 @default.
- W4387107901 hasRelatedWork W4231184955 @default.
- W4387107901 hasRelatedWork W4286615217 @default.
- W4387107901 hasRelatedWork W618293728 @default.
- W4387107901 hasVolume "135" @default.
- W4387107901 isParatext "false" @default.
- W4387107901 isRetracted "false" @default.
- W4387107901 workType "article" @default.