Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287777382> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4287777382 abstract "Over the past few years, providers such as Google, Microsoft, and Amazon have started to provide customers with access to software interfaces allowing them to easily embed machine learning tasks into their applications. Overall, organizations can now use Machine Learning as a Service (MLaaS) engines to outsource complex tasks, e.g., training classifiers, performing predictions, clustering, etc. They can also let others query models trained on their data. Naturally, this approach can also be used (and is often advocated) in other contexts, including government collaborations, citizen science projects, and business-to-business partnerships. However, if malicious users were able to recover data used to train these models, the resulting information leakage would create serious issues. Likewise, if the inner parameters of the model are considered proprietary information, then access to the model should not allow an adversary to learn such parameters. In this document, we set to review privacy challenges in this space, providing a systematic review of the relevant research literature, also exploring possible countermeasures. More specifically, we provide ample background information on relevant concepts around machine learning and privacy. Then, we discuss possible adversarial models and settings, cover a wide range of attacks that relate to private and/or sensitive information leakage, and review recent results attempting to defend against such attacks. Finally, we conclude with a list of open problems that require more work, including the need for better evaluations, more targeted defenses, and the study of the relation to policy and data protection efforts." @default.
- W4287777382 created "2022-07-26" @default.
- W4287777382 creator A5035799220 @default.
- W4287777382 date "2020-05-18" @default.
- W4287777382 modified "2023-09-25" @default.
- W4287777382 title "An Overview of Privacy in Machine Learning" @default.
- W4287777382 doi "https://doi.org/10.48550/arxiv.2005.08679" @default.
- W4287777382 hasPublicationYear "2020" @default.
- W4287777382 type Work @default.
- W4287777382 citedByCount "0" @default.
- W4287777382 crossrefType "posted-content" @default.
- W4287777382 hasAuthorship W4287777382A5035799220 @default.
- W4287777382 hasBestOaLocation W42877773821 @default.
- W4287777382 hasConcept C119857082 @default.
- W4287777382 hasConcept C124101348 @default.
- W4287777382 hasConcept C136764020 @default.
- W4287777382 hasConcept C137822555 @default.
- W4287777382 hasConcept C138885662 @default.
- W4287777382 hasConcept C140547941 @default.
- W4287777382 hasConcept C154945302 @default.
- W4287777382 hasConcept C17744445 @default.
- W4287777382 hasConcept C199539241 @default.
- W4287777382 hasConcept C2522767166 @default.
- W4287777382 hasConcept C25343380 @default.
- W4287777382 hasConcept C2778137410 @default.
- W4287777382 hasConcept C37736160 @default.
- W4287777382 hasConcept C38652104 @default.
- W4287777382 hasConcept C41008148 @default.
- W4287777382 hasConcept C41065033 @default.
- W4287777382 hasConcept C41895202 @default.
- W4287777382 hasConcept C46934059 @default.
- W4287777382 hasConceptScore W4287777382C119857082 @default.
- W4287777382 hasConceptScore W4287777382C124101348 @default.
- W4287777382 hasConceptScore W4287777382C136764020 @default.
- W4287777382 hasConceptScore W4287777382C137822555 @default.
- W4287777382 hasConceptScore W4287777382C138885662 @default.
- W4287777382 hasConceptScore W4287777382C140547941 @default.
- W4287777382 hasConceptScore W4287777382C154945302 @default.
- W4287777382 hasConceptScore W4287777382C17744445 @default.
- W4287777382 hasConceptScore W4287777382C199539241 @default.
- W4287777382 hasConceptScore W4287777382C2522767166 @default.
- W4287777382 hasConceptScore W4287777382C25343380 @default.
- W4287777382 hasConceptScore W4287777382C2778137410 @default.
- W4287777382 hasConceptScore W4287777382C37736160 @default.
- W4287777382 hasConceptScore W4287777382C38652104 @default.
- W4287777382 hasConceptScore W4287777382C41008148 @default.
- W4287777382 hasConceptScore W4287777382C41065033 @default.
- W4287777382 hasConceptScore W4287777382C41895202 @default.
- W4287777382 hasConceptScore W4287777382C46934059 @default.
- W4287777382 hasLocation W42877773821 @default.
- W4287777382 hasOpenAccess W4287777382 @default.
- W4287777382 hasPrimaryLocation W42877773821 @default.
- W4287777382 hasRelatedWork W1583236736 @default.
- W4287777382 hasRelatedWork W2018114558 @default.
- W4287777382 hasRelatedWork W2095577883 @default.
- W4287777382 hasRelatedWork W2522301850 @default.
- W4287777382 hasRelatedWork W2951487695 @default.
- W4287777382 hasRelatedWork W3024092901 @default.
- W4287777382 hasRelatedWork W3193386261 @default.
- W4287777382 hasRelatedWork W4248052496 @default.
- W4287777382 hasRelatedWork W4251088474 @default.
- W4287777382 hasRelatedWork W4287777382 @default.
- W4287777382 isParatext "false" @default.
- W4287777382 isRetracted "false" @default.
- W4287777382 workType "article" @default.