Trading accuracy for privacy in machine learning tasks: an empirical analysis

e-Archivo Repository

Show simple item record

dc.contributor.author Prodomo, Vittorio
dc.contributor.author González Sánchez, Roberto
dc.contributor.author Gramaglia, Marco
dc.date.accessioned 2022-04-19T12:36:22Z
dc.date.available 2022-04-19T12:36:22Z
dc.date.issued 2022-03-22
dc.identifier.bibliographicCitation González Sánchez, Roberto; Gramaglia, Marco; Prodomo, Vittorio. Trading accuracy for privacy in machine learning tasks: an empirical analysis. In: IEEE Conference on Communications and Network Security (CNS 2021). IEEE, March 2022, 2 p.
dc.identifier.isbn 978-1-6654-4496-5
dc.identifier.uri http://hdl.handle.net/10016/34568
dc.description Proceeding of: IEEE Conference on Communications and Network Security (CNS 2021), 4-6 Oct. 2021, Tempe, AZ, USA (Virtual conference)
dc.description.abstract Different kinds of user-generated data are increasingly used to tailor and optimize, through Machine Learning, the operation of online services and infrastructures. This typically requires sharing data among different partners, often including private data of individuals or business confidential data. While this poses privacy issues, the current state-of-the-art solutions either impose strong assumptions on the usage scenario or drastically reduce the data quality. In this paper, we evaluate through a generic framework the trade-offs between the accuracy of Machine Learning tasks and the achieved privacy (measured as similarity) on the input data, discussing trends and ways forward.
dc.description.sponsorship The work of University Carlos III of Madrid was supported by the H2020 5G-TOURS project (grant no. 856950).
dc.format.extent 2 p.
dc.language.iso eng
dc.publisher IEEE
dc.rights © 2021 IEEE.
dc.subject.other Machine Learning
dc.subject.other Privacy
dc.subject.other Trade offs
dc.title Trading accuracy for privacy in machine learning tasks: an empirical analysis
dc.type conferenceObject
dc.type bookPart
dc.subject.eciencia Telecomunicaciones
dc.identifier.doi https://doi.org/10.1109/CNS53000.2021.9729036
dc.rights.accessRights openAccess
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/856950/5G-TOURS
dc.type.version acceptedVersion
dc.relation.eventdate 2021-10-04
dc.relation.eventplace Tempe, AZ, USA (Virtual conference)
dc.relation.eventtitle IEEE Conference on Communications and Network Security (CNS 2021)
dc.relation.eventtype poster
dc.identifier.publicationfirstpage 1
dc.identifier.publicationlastpage 2
dc.identifier.publicationtitle 2021 IEEE Conference on Communications and Network Security (CNS)
dc.identifier.uxxi CC/0000032636
dc.contributor.funder European Commission
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)


This item appears in the following Collection(s)

Show simple item record