Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285113099> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4285113099 endingPage "60" @default.
- W4285113099 startingPage "48" @default.
- W4285113099 abstract "Towards the realization of a super-smart society, AI analysis methods that preserve the privacy of big data in cyberspace are being developed. From the viewpoint of developing machine learning as a secure and safe AI analysis method for users, many studies have been conducted in this field on 1) secure multiparty computation (SMC), 2) quasi-homomorphic encryption, and 3) federated learning, among other techniques. Previous studies have shown that both security and utility are essential for machine learning using confidential data. However, there is a trade-off between these two properties, and there are no known methods that satisfy both simultaneously at a high level. In this paper, as a superior method in both privacy-preserving of data and utility, we propose a learning method based on distributed processing using simple, secure, divided data and parameters. In this method, individual data and parameters are divided into multiple pieces using random numbers in advance, and each piece is stored in each server. The learning of the proposed method is achieved by using these data and parameters as they are divided and by repeating partial computations on each server and integrated computations at the central server. The advantages of the proposed method are the preservation of data privacy by not restoring the data and parameters during learning; the improvement of usability by realizing a machine learning method based on distributed processing, as federated learning does; and almost no degradation in accuracy compared to conventional methods. Based on the proposed method, we propose backpropagation and neural gas (NG) algorithms as examples of supervised and unsupervised machine learning applications. Our numerical simulation shows that these algorithms can achieve accuracy comparable to conventional models." @default.
- W4285113099 created "2022-07-14" @default.
- W4285113099 creator A5015482699 @default.
- W4285113099 creator A5021189771 @default.
- W4285113099 creator A5040337456 @default.
- W4285113099 creator A5055834741 @default.
- W4285113099 date "2022-01-01" @default.
- W4285113099 modified "2023-09-28" @default.
- W4285113099 title "Machine Learning with Distributed Processing using Secure Divided Data: Towards Privacy-Preserving Advanced AI Processing in a Super-Smart Society" @default.
- W4285113099 doi "https://doi.org/10.33969/j-nana.2022.020105" @default.
- W4285113099 hasPublicationYear "2022" @default.
- W4285113099 type Work @default.
- W4285113099 citedByCount "1" @default.
- W4285113099 countsByYear W42851130992023 @default.
- W4285113099 crossrefType "journal-article" @default.
- W4285113099 hasAuthorship W4285113099A5015482699 @default.
- W4285113099 hasAuthorship W4285113099A5021189771 @default.
- W4285113099 hasAuthorship W4285113099A5040337456 @default.
- W4285113099 hasAuthorship W4285113099A5055834741 @default.
- W4285113099 hasBestOaLocation W42851130991 @default.
- W4285113099 hasConcept C107457646 @default.
- W4285113099 hasConcept C110875604 @default.
- W4285113099 hasConcept C111919701 @default.
- W4285113099 hasConcept C119857082 @default.
- W4285113099 hasConcept C120314980 @default.
- W4285113099 hasConcept C123201435 @default.
- W4285113099 hasConcept C136764020 @default.
- W4285113099 hasConcept C138827492 @default.
- W4285113099 hasConcept C148730421 @default.
- W4285113099 hasConcept C154945302 @default.
- W4285113099 hasConcept C158338273 @default.
- W4285113099 hasConcept C170130773 @default.
- W4285113099 hasConcept C2781241145 @default.
- W4285113099 hasConcept C38652104 @default.
- W4285113099 hasConcept C41008148 @default.
- W4285113099 hasConcept C77088390 @default.
- W4285113099 hasConcept C79974875 @default.
- W4285113099 hasConceptScore W4285113099C107457646 @default.
- W4285113099 hasConceptScore W4285113099C110875604 @default.
- W4285113099 hasConceptScore W4285113099C111919701 @default.
- W4285113099 hasConceptScore W4285113099C119857082 @default.
- W4285113099 hasConceptScore W4285113099C120314980 @default.
- W4285113099 hasConceptScore W4285113099C123201435 @default.
- W4285113099 hasConceptScore W4285113099C136764020 @default.
- W4285113099 hasConceptScore W4285113099C138827492 @default.
- W4285113099 hasConceptScore W4285113099C148730421 @default.
- W4285113099 hasConceptScore W4285113099C154945302 @default.
- W4285113099 hasConceptScore W4285113099C158338273 @default.
- W4285113099 hasConceptScore W4285113099C170130773 @default.
- W4285113099 hasConceptScore W4285113099C2781241145 @default.
- W4285113099 hasConceptScore W4285113099C38652104 @default.
- W4285113099 hasConceptScore W4285113099C41008148 @default.
- W4285113099 hasConceptScore W4285113099C77088390 @default.
- W4285113099 hasConceptScore W4285113099C79974875 @default.
- W4285113099 hasIssue "1" @default.
- W4285113099 hasLocation W42851130991 @default.
- W4285113099 hasOpenAccess W4285113099 @default.
- W4285113099 hasPrimaryLocation W42851130991 @default.
- W4285113099 hasRelatedWork W2231096324 @default.
- W4285113099 hasRelatedWork W2766014396 @default.
- W4285113099 hasRelatedWork W3006130360 @default.
- W4285113099 hasRelatedWork W3109510438 @default.
- W4285113099 hasRelatedWork W3168105190 @default.
- W4285113099 hasRelatedWork W4285503642 @default.
- W4285113099 hasRelatedWork W4309969708 @default.
- W4285113099 hasRelatedWork W4311327345 @default.
- W4285113099 hasRelatedWork W4313046019 @default.
- W4285113099 hasRelatedWork W4321510660 @default.
- W4285113099 hasVolume "2" @default.
- W4285113099 isParatext "false" @default.
- W4285113099 isRetracted "false" @default.
- W4285113099 workType "article" @default.