Matches in SemOpenAlex for { <https://semopenalex.org/work/W2974192836> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2974192836 endingPage "25" @default.
- W2974192836 startingPage "17" @default.
- W2974192836 abstract "Here we consider a common data encryption problem encountered by users who want to disclose some data to gain utility but preserve their private information. Specifically, we consider the inference attack, in which an adversary conducts inference on the disclosed data to gain information about users’ private data. Following privacy funnel (Makhdoumi et al., 2014), assuming that the original data X is transformed into Z before disclosing and the log loss is used for both privacy and utility metrics, then the problem can be modeled as finding a mapping X→Z that maximizes mutual information between X and Z subject to a constraint that the mutual information between Z and private data S is smaller than a predefined threshold ϵ. In contrast to the original study (Makhdoumi et al., 2014), which only focused on discrete data, we consider the more general and practical setting of continuous and high-dimensional disclosed data (e.g., image data). Most previous work on privacy-preserving representation learning is based on adversarial learning or generative adversarial networks, which has been shown to suffer from the vanishing gradient problem, and it is experimentally difficult to eliminate the relationship with private data Y when Z is constrained to retain more information about X. Here we propose a simple but effective variational approach that does not rely on adversarial training. Our experimental results show that our approach is stable and outperforms previous methods in terms of both downstream task accuracy and mutual information estimation." @default.
- W2974192836 created "2019-09-26" @default.
- W2974192836 creator A5001819736 @default.
- W2974192836 creator A5054829309 @default.
- W2974192836 date "2020-03-01" @default.
- W2974192836 modified "2023-10-14" @default.
- W2974192836 title "Variational approach for privacy funnel optimization on continuous data" @default.
- W2974192836 cites W2092939357 @default.
- W2974192836 cites W2149350210 @default.
- W2974192836 cites W2564029303 @default.
- W2974192836 cites W2963278610 @default.
- W2974192836 cites W2963830550 @default.
- W2974192836 cites W2963879260 @default.
- W2974192836 cites W3099111404 @default.
- W2974192836 doi "https://doi.org/10.1016/j.jpdc.2019.09.010" @default.
- W2974192836 hasPublicationYear "2020" @default.
- W2974192836 type Work @default.
- W2974192836 sameAs 2974192836 @default.
- W2974192836 citedByCount "4" @default.
- W2974192836 countsByYear W29741928362020 @default.
- W2974192836 countsByYear W29741928362021 @default.
- W2974192836 countsByYear W29741928362022 @default.
- W2974192836 crossrefType "journal-article" @default.
- W2974192836 hasAuthorship W2974192836A5001819736 @default.
- W2974192836 hasAuthorship W2974192836A5054829309 @default.
- W2974192836 hasConcept C11413529 @default.
- W2974192836 hasConcept C124101348 @default.
- W2974192836 hasConcept C137822555 @default.
- W2974192836 hasConcept C148730421 @default.
- W2974192836 hasConcept C152139883 @default.
- W2974192836 hasConcept C154945302 @default.
- W2974192836 hasConcept C167966045 @default.
- W2974192836 hasConcept C17744445 @default.
- W2974192836 hasConcept C199539241 @default.
- W2974192836 hasConcept C23130292 @default.
- W2974192836 hasConcept C2524010 @default.
- W2974192836 hasConcept C2776036281 @default.
- W2974192836 hasConcept C2776214188 @default.
- W2974192836 hasConcept C2776359362 @default.
- W2974192836 hasConcept C33923547 @default.
- W2974192836 hasConcept C37736160 @default.
- W2974192836 hasConcept C38652104 @default.
- W2974192836 hasConcept C39890363 @default.
- W2974192836 hasConcept C41008148 @default.
- W2974192836 hasConcept C80444323 @default.
- W2974192836 hasConcept C94625758 @default.
- W2974192836 hasConcept C99221444 @default.
- W2974192836 hasConceptScore W2974192836C11413529 @default.
- W2974192836 hasConceptScore W2974192836C124101348 @default.
- W2974192836 hasConceptScore W2974192836C137822555 @default.
- W2974192836 hasConceptScore W2974192836C148730421 @default.
- W2974192836 hasConceptScore W2974192836C152139883 @default.
- W2974192836 hasConceptScore W2974192836C154945302 @default.
- W2974192836 hasConceptScore W2974192836C167966045 @default.
- W2974192836 hasConceptScore W2974192836C17744445 @default.
- W2974192836 hasConceptScore W2974192836C199539241 @default.
- W2974192836 hasConceptScore W2974192836C23130292 @default.
- W2974192836 hasConceptScore W2974192836C2524010 @default.
- W2974192836 hasConceptScore W2974192836C2776036281 @default.
- W2974192836 hasConceptScore W2974192836C2776214188 @default.
- W2974192836 hasConceptScore W2974192836C2776359362 @default.
- W2974192836 hasConceptScore W2974192836C33923547 @default.
- W2974192836 hasConceptScore W2974192836C37736160 @default.
- W2974192836 hasConceptScore W2974192836C38652104 @default.
- W2974192836 hasConceptScore W2974192836C39890363 @default.
- W2974192836 hasConceptScore W2974192836C41008148 @default.
- W2974192836 hasConceptScore W2974192836C80444323 @default.
- W2974192836 hasConceptScore W2974192836C94625758 @default.
- W2974192836 hasConceptScore W2974192836C99221444 @default.
- W2974192836 hasFunder F4320334704 @default.
- W2974192836 hasLocation W29741928361 @default.
- W2974192836 hasOpenAccess W2974192836 @default.
- W2974192836 hasPrimaryLocation W29741928361 @default.
- W2974192836 hasRelatedWork W2497748696 @default.
- W2974192836 hasRelatedWork W2616769016 @default.
- W2974192836 hasRelatedWork W2888346651 @default.
- W2974192836 hasRelatedWork W2964332492 @default.
- W2974192836 hasRelatedWork W3035323658 @default.
- W2974192836 hasRelatedWork W3082340300 @default.
- W2974192836 hasRelatedWork W3153523320 @default.
- W2974192836 hasRelatedWork W4226315217 @default.
- W2974192836 hasRelatedWork W4285230500 @default.
- W2974192836 hasRelatedWork W4288019264 @default.
- W2974192836 hasVolume "137" @default.
- W2974192836 isParatext "false" @default.
- W2974192836 isRetracted "false" @default.
- W2974192836 magId "2974192836" @default.
- W2974192836 workType "article" @default.