dc.contributor.author
Boenisch, Franziska
dc.date.accessioned
2022-02-03T09:23:46Z
dc.date.available
2022-02-03T09:23:46Z
dc.identifier.uri
https://refubium.fu-berlin.de/handle/fub188/32523
dc.identifier.uri
http://dx.doi.org/10.17169/refubium-32247
dc.description.abstract
Machine learning (ML) models are applied in an increasing variety of domains.
The availability of large amounts of data and computational resources encourages the development of ever more complex and valuable models.
These models are considered intellectual property of the legitimate parties who have trained them, which makes their protection against stealing, illegitimate redistribution, and unauthorized application an urgent need.
Digital watermarking presents a strong mechanism for marking model ownership and, thereby, offers protection against those threats.
This work presents a taxonomy identifying and analyzing different classes of watermarking schemes for ML models.
It introduces a unified threat model to allow structured reasoning on and comparison of the effectiveness of watermarking methods in different scenarios.
Furthermore, it systematizes desired security requirements and attacks against ML model watermarking.
Based on that framework, representative literature from the field is surveyed to illustrate the taxonomy.
Finally, shortcomings and general limitations of existing approaches are discussed, and an outlook on future research directions is given.
en
dc.format.extent
16 Seiten
dc.rights.uri
https://creativecommons.org/licenses/by/4.0/
dc.subject
neural networks
en
dc.subject
intellectual property protection
en
dc.subject
Watermarking
en
dc.subject
machine learning
en
dc.subject
model stealing
en
dc.subject.ddc
500 Naturwissenschaften und Mathematik::510 Mathematik::510 Mathematik
dc.title
A Systematic Review on Model Watermarking for Neural Networks
dc.type
Wissenschaftlicher Artikel
dcterms.bibliographicCitation.articlenumber
729663
dcterms.bibliographicCitation.doi
10.3389/fdata.2021.729663
dcterms.bibliographicCitation.journaltitle
Frontiers in Big Data
dcterms.bibliographicCitation.journaltitle
Frontiers in Big Data
dcterms.bibliographicCitation.volume
4
dcterms.bibliographicCitation.url
https://doi.org/10.3389/fdata.2021.729663
refubium.affiliation
Mathematik und Informatik
refubium.affiliation.other
Institut für Informatik

refubium.resourceType.isindependentpub
no
dcterms.accessRights.openaire
open access
dcterms.isPartOf.eissn
2624-909X