Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313173408> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4313173408 endingPage "14" @default.
- W4313173408 startingPage "1" @default.
- W4313173408 abstract "Privacy protection and incentive mechanism are two fundamental problems in federated learning (FL), which aim at protecting the privacy of data owners and stimulating them to share more resources, respectively. Recent works have proposed differential privacy (DP) based privacy-preserving incentive mechanisms to solve both problems simultaneously. However, almost all of them took the privacy level as the only incentive item, without considering other factors, such as data quantity and quality. Moreover, an untrusted server can further infer sensitive information from the bids that reflect the true costs of data owners. To solve these problems, in this paper, we propose a dual-privacy preserving and quality-aware incentive mechanism, PrivAim, for federated learning. Specifically, it utilizes differential privacy to protect the local models and true costs against the untrusted parameter server, and carefully designs a multi-dimensional reverse auction mechanism to incentivize data owners with high quality and low cost to participate in FL without knowing the true bids. We theoretically prove that PrivAim satisfies <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink><tex-math notation=LaTeX>$Delta b$</tex-math></inline-formula> -truthfulness, individual rational, computational efficiency, and differential privacy. Extensive experiments show that PrivAim can effectively protect bid privacy, and achieve at least 21% and 6% improvement on social welfare and model accuracy, respectively, compared to the state-of-the-art." @default.
- W4313173408 created "2023-01-06" @default.
- W4313173408 creator A5015321037 @default.
- W4313173408 creator A5015419107 @default.
- W4313173408 creator A5069049205 @default.
- W4313173408 creator A5088104037 @default.
- W4313173408 creator A5090779839 @default.
- W4313173408 date "2022-01-01" @default.
- W4313173408 modified "2023-09-27" @default.
- W4313173408 title "PrivAim: A Dual-Privacy Preserving and Quality-Aware Incentive Mechanism for Federated Learning" @default.
- W4313173408 doi "https://doi.org/10.1109/tc.2022.3230904" @default.
- W4313173408 hasPublicationYear "2022" @default.
- W4313173408 type Work @default.
- W4313173408 citedByCount "1" @default.
- W4313173408 countsByYear W43131734082023 @default.
- W4313173408 crossrefType "journal-article" @default.
- W4313173408 hasAuthorship W4313173408A5015321037 @default.
- W4313173408 hasAuthorship W4313173408A5015419107 @default.
- W4313173408 hasAuthorship W4313173408A5069049205 @default.
- W4313173408 hasAuthorship W4313173408A5088104037 @default.
- W4313173408 hasAuthorship W4313173408A5090779839 @default.
- W4313173408 hasConcept C102938260 @default.
- W4313173408 hasConcept C111472728 @default.
- W4313173408 hasConcept C111919701 @default.
- W4313173408 hasConcept C123201435 @default.
- W4313173408 hasConcept C124101348 @default.
- W4313173408 hasConcept C124952713 @default.
- W4313173408 hasConcept C138885662 @default.
- W4313173408 hasConcept C142362112 @default.
- W4313173408 hasConcept C144237770 @default.
- W4313173408 hasConcept C153517567 @default.
- W4313173408 hasConcept C162324750 @default.
- W4313173408 hasConcept C175444787 @default.
- W4313173408 hasConcept C23130292 @default.
- W4313173408 hasConcept C2779530757 @default.
- W4313173408 hasConcept C2780980858 @default.
- W4313173408 hasConcept C29122968 @default.
- W4313173408 hasConcept C33923547 @default.
- W4313173408 hasConcept C38652104 @default.
- W4313173408 hasConcept C41008148 @default.
- W4313173408 hasConcept C68387754 @default.
- W4313173408 hasConceptScore W4313173408C102938260 @default.
- W4313173408 hasConceptScore W4313173408C111472728 @default.
- W4313173408 hasConceptScore W4313173408C111919701 @default.
- W4313173408 hasConceptScore W4313173408C123201435 @default.
- W4313173408 hasConceptScore W4313173408C124101348 @default.
- W4313173408 hasConceptScore W4313173408C124952713 @default.
- W4313173408 hasConceptScore W4313173408C138885662 @default.
- W4313173408 hasConceptScore W4313173408C142362112 @default.
- W4313173408 hasConceptScore W4313173408C144237770 @default.
- W4313173408 hasConceptScore W4313173408C153517567 @default.
- W4313173408 hasConceptScore W4313173408C162324750 @default.
- W4313173408 hasConceptScore W4313173408C175444787 @default.
- W4313173408 hasConceptScore W4313173408C23130292 @default.
- W4313173408 hasConceptScore W4313173408C2779530757 @default.
- W4313173408 hasConceptScore W4313173408C2780980858 @default.
- W4313173408 hasConceptScore W4313173408C29122968 @default.
- W4313173408 hasConceptScore W4313173408C33923547 @default.
- W4313173408 hasConceptScore W4313173408C38652104 @default.
- W4313173408 hasConceptScore W4313173408C41008148 @default.
- W4313173408 hasConceptScore W4313173408C68387754 @default.
- W4313173408 hasLocation W43131734081 @default.
- W4313173408 hasOpenAccess W4313173408 @default.
- W4313173408 hasPrimaryLocation W43131734081 @default.
- W4313173408 hasRelatedWork W1604044185 @default.
- W4313173408 hasRelatedWork W1976989753 @default.
- W4313173408 hasRelatedWork W1991020079 @default.
- W4313173408 hasRelatedWork W2885673189 @default.
- W4313173408 hasRelatedWork W2889815322 @default.
- W4313173408 hasRelatedWork W2921852975 @default.
- W4313173408 hasRelatedWork W3087173950 @default.
- W4313173408 hasRelatedWork W3115158925 @default.
- W4313173408 hasRelatedWork W4243286777 @default.
- W4313173408 hasRelatedWork W4312905226 @default.
- W4313173408 isParatext "false" @default.
- W4313173408 isRetracted "false" @default.
- W4313173408 workType "article" @default.