Matches in SemOpenAlex for { <https://semopenalex.org/work/W3208583946> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3208583946 endingPage "102506" @default.
- W3208583946 startingPage "102506" @default.
- W3208583946 abstract "We study the question of how well machine learning (ML) models trained on a certain data set provide privacy for the training data, or equivalently, whether it is possible to reverse-engineer the training data from a given ML model. While this is easy to answer negatively in the most general case, it is interesting to note that the protection extends over non-recoverability towards plausible deniability: Given an ML model $f$, we show that one can take a set of purely random training data, and from this define a suitable ``learning rule'' that will produce a ML model that is exactly $f$. Thus, any speculation about which data has been used to train $f$ is deniable upon the claim that any other data could have led to the same results. We corroborate our theoretical finding with practical examples, and open source implementations of how to find the learning rules for a chosen set of raining data." @default.
- W3208583946 created "2021-11-08" @default.
- W3208583946 creator A5008004764 @default.
- W3208583946 creator A5017498019 @default.
- W3208583946 creator A5026312652 @default.
- W3208583946 creator A5045057070 @default.
- W3208583946 creator A5082964903 @default.
- W3208583946 date "2022-01-01" @default.
- W3208583946 modified "2023-09-26" @default.
- W3208583946 title "Supervised Machine Learning with Plausible Deniability" @default.
- W3208583946 cites W2010053513 @default.
- W3208583946 cites W2106432414 @default.
- W3208583946 cites W2509467699 @default.
- W3208583946 cites W2584956383 @default.
- W3208583946 cites W2790448487 @default.
- W3208583946 cites W2799040448 @default.
- W3208583946 cites W2883113615 @default.
- W3208583946 cites W3099320515 @default.
- W3208583946 cites W3103802018 @default.
- W3208583946 doi "https://doi.org/10.1016/j.cose.2021.102506" @default.
- W3208583946 hasPublicationYear "2022" @default.
- W3208583946 type Work @default.
- W3208583946 sameAs 3208583946 @default.
- W3208583946 citedByCount "1" @default.
- W3208583946 countsByYear W32085839462022 @default.
- W3208583946 crossrefType "journal-article" @default.
- W3208583946 hasAuthorship W3208583946A5008004764 @default.
- W3208583946 hasAuthorship W3208583946A5017498019 @default.
- W3208583946 hasAuthorship W3208583946A5026312652 @default.
- W3208583946 hasAuthorship W3208583946A5045057070 @default.
- W3208583946 hasAuthorship W3208583946A5082964903 @default.
- W3208583946 hasBestOaLocation W32085839462 @default.
- W3208583946 hasConcept C119857082 @default.
- W3208583946 hasConcept C136389625 @default.
- W3208583946 hasConcept C139719470 @default.
- W3208583946 hasConcept C154945302 @default.
- W3208583946 hasConcept C162324750 @default.
- W3208583946 hasConcept C177264268 @default.
- W3208583946 hasConcept C199360897 @default.
- W3208583946 hasConcept C26713055 @default.
- W3208583946 hasConcept C41008148 @default.
- W3208583946 hasConcept C47941915 @default.
- W3208583946 hasConcept C50644808 @default.
- W3208583946 hasConcept C51632099 @default.
- W3208583946 hasConcept C58489278 @default.
- W3208583946 hasConceptScore W3208583946C119857082 @default.
- W3208583946 hasConceptScore W3208583946C136389625 @default.
- W3208583946 hasConceptScore W3208583946C139719470 @default.
- W3208583946 hasConceptScore W3208583946C154945302 @default.
- W3208583946 hasConceptScore W3208583946C162324750 @default.
- W3208583946 hasConceptScore W3208583946C177264268 @default.
- W3208583946 hasConceptScore W3208583946C199360897 @default.
- W3208583946 hasConceptScore W3208583946C26713055 @default.
- W3208583946 hasConceptScore W3208583946C41008148 @default.
- W3208583946 hasConceptScore W3208583946C47941915 @default.
- W3208583946 hasConceptScore W3208583946C50644808 @default.
- W3208583946 hasConceptScore W3208583946C51632099 @default.
- W3208583946 hasConceptScore W3208583946C58489278 @default.
- W3208583946 hasLocation W32085839461 @default.
- W3208583946 hasLocation W32085839462 @default.
- W3208583946 hasLocation W32085839463 @default.
- W3208583946 hasLocation W32085839464 @default.
- W3208583946 hasOpenAccess W3208583946 @default.
- W3208583946 hasPrimaryLocation W32085839461 @default.
- W3208583946 hasRelatedWork W2971361125 @default.
- W3208583946 hasRelatedWork W3018465876 @default.
- W3208583946 hasRelatedWork W3046775127 @default.
- W3208583946 hasRelatedWork W3094076422 @default.
- W3208583946 hasRelatedWork W3162567751 @default.
- W3208583946 hasRelatedWork W3167317451 @default.
- W3208583946 hasRelatedWork W4220686584 @default.
- W3208583946 hasRelatedWork W4221088574 @default.
- W3208583946 hasRelatedWork W4285260836 @default.
- W3208583946 hasRelatedWork W4319309271 @default.
- W3208583946 hasVolume "112" @default.
- W3208583946 isParatext "false" @default.
- W3208583946 isRetracted "false" @default.
- W3208583946 magId "3208583946" @default.
- W3208583946 workType "article" @default.