Matches in SemOpenAlex for { <https://semopenalex.org/work/W4205366980> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W4205366980 endingPage "252" @default.
- W4205366980 startingPage "237" @default.
- W4205366980 abstract "The advances in machine learning have revealed its great potential for emerging mobile applications such as face recognition and voice assistant. Models trained via a Neural Network (NN) can offer accurate and efficient inference services for mobile users. Unfortunately, the current deployment of such service encounters privacy concerns. Directly offloading the model to the mobile device violates model privacy of the model owner, while feeding user input to the service compromises user privacy. To address this issue, we propose Leia, a lightweight cryptographic NN inference system at the edge. Leia is designed from two mobile-friendly perspectives. First, it leverages the paradigm of edge computing wherein the inference procedure keeps the model closer to the mobile user to foster low latency service. Specifically, Leia’s architecture consists of two non-colluding edge services to obliviously perform NN inference on the encoded user data and model. Second, Leia’s realization makes the judicious use of potentially constrained computational and communication resources in edge devices. We adapt the Binarized Neural Network (BNN), a trending flavor of NN with low inference overhead, and purely choose the lightweight secret sharing techniques to realize secure blocks of BNN. We implement Leia and deploy it on Raspberry Pi. Empirical evaluations on benchmark and medical datasets via various models demonstrate the practicality of Leia." @default.
- W4205366980 created "2022-01-26" @default.
- W4205366980 creator A5012701826 @default.
- W4205366980 creator A5054012901 @default.
- W4205366980 creator A5064553444 @default.
- W4205366980 creator A5067053626 @default.
- W4205366980 date "2022-01-01" @default.
- W4205366980 modified "2023-10-18" @default.
- W4205366980 title "Leia: A Lightweight Cryptographic Neural Network Inference System at the Edge" @default.
- W4205366980 cites W1499934958 @default.
- W4205366980 cites W1969009977 @default.
- W4205366980 cites W2019891719 @default.
- W4205366980 cites W2047370889 @default.
- W4205366980 cites W2135297873 @default.
- W4205366980 cites W2701059868 @default.
- W4205366980 cites W2765200655 @default.
- W4205366980 cites W2953483183 @default.
- W4205366980 cites W2963106566 @default.
- W4205366980 cites W2963752132 @default.
- W4205366980 cites W2964261135 @default.
- W4205366980 cites W2969373235 @default.
- W4205366980 cites W2981672041 @default.
- W4205366980 cites W2983440318 @default.
- W4205366980 cites W2984644945 @default.
- W4205366980 cites W3003532255 @default.
- W4205366980 cites W3033548151 @default.
- W4205366980 cites W3081957293 @default.
- W4205366980 cites W3102360395 @default.
- W4205366980 cites W3108146280 @default.
- W4205366980 cites W3112297092 @default.
- W4205366980 cites W3175868174 @default.
- W4205366980 doi "https://doi.org/10.1109/tifs.2021.3138611" @default.
- W4205366980 hasPublicationYear "2022" @default.
- W4205366980 type Work @default.
- W4205366980 citedByCount "6" @default.
- W4205366980 countsByYear W42053669802022 @default.
- W4205366980 countsByYear W42053669802023 @default.
- W4205366980 crossrefType "journal-article" @default.
- W4205366980 hasAuthorship W4205366980A5012701826 @default.
- W4205366980 hasAuthorship W4205366980A5054012901 @default.
- W4205366980 hasAuthorship W4205366980A5064553444 @default.
- W4205366980 hasAuthorship W4205366980A5067053626 @default.
- W4205366980 hasConcept C111919701 @default.
- W4205366980 hasConcept C119857082 @default.
- W4205366980 hasConcept C120314980 @default.
- W4205366980 hasConcept C136764020 @default.
- W4205366980 hasConcept C138236772 @default.
- W4205366980 hasConcept C144543869 @default.
- W4205366980 hasConcept C154945302 @default.
- W4205366980 hasConcept C162307627 @default.
- W4205366980 hasConcept C178489894 @default.
- W4205366980 hasConcept C186967261 @default.
- W4205366980 hasConcept C2776214188 @default.
- W4205366980 hasConcept C2778456923 @default.
- W4205366980 hasConcept C2779960059 @default.
- W4205366980 hasConcept C31258907 @default.
- W4205366980 hasConcept C38652104 @default.
- W4205366980 hasConcept C41008148 @default.
- W4205366980 hasConcept C79974875 @default.
- W4205366980 hasConcept C93996380 @default.
- W4205366980 hasConceptScore W4205366980C111919701 @default.
- W4205366980 hasConceptScore W4205366980C119857082 @default.
- W4205366980 hasConceptScore W4205366980C120314980 @default.
- W4205366980 hasConceptScore W4205366980C136764020 @default.
- W4205366980 hasConceptScore W4205366980C138236772 @default.
- W4205366980 hasConceptScore W4205366980C144543869 @default.
- W4205366980 hasConceptScore W4205366980C154945302 @default.
- W4205366980 hasConceptScore W4205366980C162307627 @default.
- W4205366980 hasConceptScore W4205366980C178489894 @default.
- W4205366980 hasConceptScore W4205366980C186967261 @default.
- W4205366980 hasConceptScore W4205366980C2776214188 @default.
- W4205366980 hasConceptScore W4205366980C2778456923 @default.
- W4205366980 hasConceptScore W4205366980C2779960059 @default.
- W4205366980 hasConceptScore W4205366980C31258907 @default.
- W4205366980 hasConceptScore W4205366980C38652104 @default.
- W4205366980 hasConceptScore W4205366980C41008148 @default.
- W4205366980 hasConceptScore W4205366980C79974875 @default.
- W4205366980 hasConceptScore W4205366980C93996380 @default.
- W4205366980 hasFunder F4320334704 @default.
- W4205366980 hasLocation W42053669801 @default.
- W4205366980 hasOpenAccess W4205366980 @default.
- W4205366980 hasPrimaryLocation W42053669801 @default.
- W4205366980 hasRelatedWork W1990379658 @default.
- W4205366980 hasRelatedWork W2785873404 @default.
- W4205366980 hasRelatedWork W2917288403 @default.
- W4205366980 hasRelatedWork W2945616868 @default.
- W4205366980 hasRelatedWork W2981507084 @default.
- W4205366980 hasRelatedWork W3185591558 @default.
- W4205366980 hasRelatedWork W4205704103 @default.
- W4205366980 hasRelatedWork W4225693843 @default.
- W4205366980 hasRelatedWork W4312540714 @default.
- W4205366980 hasRelatedWork W4313145167 @default.
- W4205366980 hasVolume "17" @default.
- W4205366980 isParatext "false" @default.
- W4205366980 isRetracted "false" @default.
- W4205366980 workType "article" @default.