Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387421261> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4387421261 abstract "This research deals with how to build reliable AI models using shared sensitive data. Confidential computing is gaining attention in AI services for a ubiquitous computing field. It makes legal and social regulations strict, including protecting privacy and ensuring security for sensitive data and AI models. As is also the case in ubiquitous computing research. The research phase also requires a manual trial-and-error process to create value through new combinations of shared data and AI models. Conventional confidential computing cannot realize the human workflow. This paper proposes and verifies “Sandbox AI” that can build precise AI models through efficient manual processes without revealing the shared data or models to one another. Sandbox AI utilizes privacy-preserving synthetic data generation and active learning on a confidential computing architecture. Specifically, Sandbox AI works in a sandbox container and generates synthetic data on the basis of real data, interactively extracts synthetic data that are useful for efficient model training while considering the real data distribution, discloses only the extracted synthetic data for annotation, and re-trains the model on the labeled synthetic data. Experimental results show that the achieved model accuracy is as good as that of conventional learning using real data with privacy violations." @default.
- W4387421261 created "2023-10-08" @default.
- W4387421261 creator A5002308870 @default.
- W4387421261 creator A5028050904 @default.
- W4387421261 creator A5035913993 @default.
- W4387421261 creator A5065023796 @default.
- W4387421261 creator A5083627580 @default.
- W4387421261 date "2023-10-08" @default.
- W4387421261 modified "2023-10-10" @default.
- W4387421261 title "Sandbox AI: We Don't Trust Each Other but Want to Create New Value Efficiently Through Collaboration Using Sensitive Data" @default.
- W4387421261 cites W2159024459 @default.
- W4387421261 cites W2294382750 @default.
- W4387421261 cites W2343514605 @default.
- W4387421261 cites W2541743403 @default.
- W4387421261 cites W2911978475 @default.
- W4387421261 cites W2915252171 @default.
- W4387421261 cites W3038041229 @default.
- W4387421261 cites W3071470454 @default.
- W4387421261 cites W3166254754 @default.
- W4387421261 cites W3190683899 @default.
- W4387421261 cites W4214487284 @default.
- W4387421261 cites W4234726042 @default.
- W4387421261 cites W4280616277 @default.
- W4387421261 cites W4281920725 @default.
- W4387421261 cites W4290945397 @default.
- W4387421261 cites W4365809852 @default.
- W4387421261 cites W4382239433 @default.
- W4387421261 cites W4382318631 @default.
- W4387421261 doi "https://doi.org/10.1145/3594739.3610693" @default.
- W4387421261 hasPublicationYear "2023" @default.
- W4387421261 type Work @default.
- W4387421261 citedByCount "0" @default.
- W4387421261 crossrefType "proceedings-article" @default.
- W4387421261 hasAuthorship W4387421261A5002308870 @default.
- W4387421261 hasAuthorship W4387421261A5028050904 @default.
- W4387421261 hasAuthorship W4387421261A5035913993 @default.
- W4387421261 hasAuthorship W4387421261A5065023796 @default.
- W4387421261 hasAuthorship W4387421261A5083627580 @default.
- W4387421261 hasConcept C115903868 @default.
- W4387421261 hasConcept C119857082 @default.
- W4387421261 hasConcept C123201435 @default.
- W4387421261 hasConcept C154945302 @default.
- W4387421261 hasConcept C160920958 @default.
- W4387421261 hasConcept C167981075 @default.
- W4387421261 hasConcept C177212765 @default.
- W4387421261 hasConcept C202444582 @default.
- W4387421261 hasConcept C33923547 @default.
- W4387421261 hasConcept C38652104 @default.
- W4387421261 hasConcept C41008148 @default.
- W4387421261 hasConcept C71745522 @default.
- W4387421261 hasConcept C77088390 @default.
- W4387421261 hasConcept C9652623 @default.
- W4387421261 hasConceptScore W4387421261C115903868 @default.
- W4387421261 hasConceptScore W4387421261C119857082 @default.
- W4387421261 hasConceptScore W4387421261C123201435 @default.
- W4387421261 hasConceptScore W4387421261C154945302 @default.
- W4387421261 hasConceptScore W4387421261C160920958 @default.
- W4387421261 hasConceptScore W4387421261C167981075 @default.
- W4387421261 hasConceptScore W4387421261C177212765 @default.
- W4387421261 hasConceptScore W4387421261C202444582 @default.
- W4387421261 hasConceptScore W4387421261C33923547 @default.
- W4387421261 hasConceptScore W4387421261C38652104 @default.
- W4387421261 hasConceptScore W4387421261C41008148 @default.
- W4387421261 hasConceptScore W4387421261C71745522 @default.
- W4387421261 hasConceptScore W4387421261C77088390 @default.
- W4387421261 hasConceptScore W4387421261C9652623 @default.
- W4387421261 hasLocation W43874212611 @default.
- W4387421261 hasOpenAccess W4387421261 @default.
- W4387421261 hasPrimaryLocation W43874212611 @default.
- W4387421261 hasRelatedWork W1531601525 @default.
- W4387421261 hasRelatedWork W2033352828 @default.
- W4387421261 hasRelatedWork W2355810117 @default.
- W4387421261 hasRelatedWork W2758277628 @default.
- W4387421261 hasRelatedWork W2935909890 @default.
- W4387421261 hasRelatedWork W2948807893 @default.
- W4387421261 hasRelatedWork W3173606202 @default.
- W4387421261 hasRelatedWork W3183948672 @default.
- W4387421261 hasRelatedWork W2778153218 @default.
- W4387421261 hasRelatedWork W3110381201 @default.
- W4387421261 isParatext "false" @default.
- W4387421261 isRetracted "false" @default.
- W4387421261 workType "article" @default.