Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212288271> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W3212288271 abstract "Deep learning is becoming the latest trend in sensitive applications, such as healthcare, criminal justice, and finance. As these new applications emerge, adversaries are developing ways to circumvent them. In this paper, we investigate users' revealing data to the public; parts of it are often sensitive when compactly represented. The representation should ensure that the target information is served accurately and reliably while simultaneously safeguarding sensitive information. In order to achieve that goal, we present a supervised deep learning framework based on the Information Bottleneck (IB) principle. The purpose of this was to maximize the mutual information between utility labels, and the learned compressing representation while minimizing the mutual information between the learned compressing representation and the original representation. Additionally, we examine a distributed learning framework to securely aggregate data from the Internet of Things (IoT) devices and create a utility model that is compatible with IoT devices. We apply the variational mutual information approximation to gain an accurate representation of bottlenecks. Through experiments with synthetic datasets, we demonstrate the efficiency and privacy-preserving capabilities of our framework." @default.
- W3212288271 created "2021-11-22" @default.
- W3212288271 creator A5012438164 @default.
- W3212288271 creator A5041101317 @default.
- W3212288271 date "2021-10-25" @default.
- W3212288271 modified "2023-10-16" @default.
- W3212288271 title "Distributed Variational Information Bottleneck for IOT Environments" @default.
- W3212288271 cites W2031738616 @default.
- W3212288271 cites W2034009564 @default.
- W3212288271 cites W2123469175 @default.
- W3212288271 cites W2172852798 @default.
- W3212288271 cites W2592929672 @default.
- W3212288271 cites W3037162780 @default.
- W3212288271 cites W3046653923 @default.
- W3212288271 cites W3106311775 @default.
- W3212288271 cites W3116673053 @default.
- W3212288271 cites W4205228770 @default.
- W3212288271 doi "https://doi.org/10.1109/mlsp52302.2021.9596553" @default.
- W3212288271 hasPublicationYear "2021" @default.
- W3212288271 type Work @default.
- W3212288271 sameAs 3212288271 @default.
- W3212288271 citedByCount "1" @default.
- W3212288271 countsByYear W32122882712023 @default.
- W3212288271 crossrefType "proceedings-article" @default.
- W3212288271 hasAuthorship W3212288271A5012438164 @default.
- W3212288271 hasAuthorship W3212288271A5041101317 @default.
- W3212288271 hasConcept C120314980 @default.
- W3212288271 hasConcept C137822555 @default.
- W3212288271 hasConcept C149635348 @default.
- W3212288271 hasConcept C152139883 @default.
- W3212288271 hasConcept C154945302 @default.
- W3212288271 hasConcept C159985019 @default.
- W3212288271 hasConcept C17744445 @default.
- W3212288271 hasConcept C192562407 @default.
- W3212288271 hasConcept C199539241 @default.
- W3212288271 hasConcept C2522767166 @default.
- W3212288271 hasConcept C2776359362 @default.
- W3212288271 hasConcept C2780513914 @default.
- W3212288271 hasConcept C38652104 @default.
- W3212288271 hasConcept C41008148 @default.
- W3212288271 hasConcept C4679612 @default.
- W3212288271 hasConcept C60008888 @default.
- W3212288271 hasConcept C94625758 @default.
- W3212288271 hasConceptScore W3212288271C120314980 @default.
- W3212288271 hasConceptScore W3212288271C137822555 @default.
- W3212288271 hasConceptScore W3212288271C149635348 @default.
- W3212288271 hasConceptScore W3212288271C152139883 @default.
- W3212288271 hasConceptScore W3212288271C154945302 @default.
- W3212288271 hasConceptScore W3212288271C159985019 @default.
- W3212288271 hasConceptScore W3212288271C17744445 @default.
- W3212288271 hasConceptScore W3212288271C192562407 @default.
- W3212288271 hasConceptScore W3212288271C199539241 @default.
- W3212288271 hasConceptScore W3212288271C2522767166 @default.
- W3212288271 hasConceptScore W3212288271C2776359362 @default.
- W3212288271 hasConceptScore W3212288271C2780513914 @default.
- W3212288271 hasConceptScore W3212288271C38652104 @default.
- W3212288271 hasConceptScore W3212288271C41008148 @default.
- W3212288271 hasConceptScore W3212288271C4679612 @default.
- W3212288271 hasConceptScore W3212288271C60008888 @default.
- W3212288271 hasConceptScore W3212288271C94625758 @default.
- W3212288271 hasLocation W32122882711 @default.
- W3212288271 hasOpenAccess W3212288271 @default.
- W3212288271 hasPrimaryLocation W32122882711 @default.
- W3212288271 hasRelatedWork W2103723258 @default.
- W3212288271 hasRelatedWork W2783047733 @default.
- W3212288271 hasRelatedWork W2982402336 @default.
- W3212288271 hasRelatedWork W2989653627 @default.
- W3212288271 hasRelatedWork W2996503800 @default.
- W3212288271 hasRelatedWork W3098272089 @default.
- W3212288271 hasRelatedWork W3133902514 @default.
- W3212288271 hasRelatedWork W3161880184 @default.
- W3212288271 hasRelatedWork W3212288271 @default.
- W3212288271 hasRelatedWork W4285529594 @default.
- W3212288271 isParatext "false" @default.
- W3212288271 isRetracted "false" @default.
- W3212288271 magId "3212288271" @default.
- W3212288271 workType "article" @default.