Protecting artificial intelligence IPs: a survey of watermarking and fingerprinting for machine learning

Simple item page
dc.contributor.authorRegazzoni, Francesco
dc.contributor.authorPalmieri, Paolo
dc.contributor.authorSmailbegovic, Fethulah
dc.contributor.authorCammarota, Rosario
dc.contributor.authorPolian, Ilia
dc.contributor.funderHorizon 2020en
dc.contributor.funderScience Foundation Irelanden
dc.date.accessioned2021-09-29T14:07:20Z
dc.date.available2021-09-29T14:07:20Z
dc.date.issued2021-04-04
dc.date.updated2021-09-29T10:03:20Z
dc.description.abstractArtificial intelligence (AI) algorithms achieve outstanding results in many application domains such as computer vision and natural language processing. The performance of AI models is the outcome of complex and costly model architecture design and training processes. Hence, it is paramount for model owners to protect their AI models from piracy – model cloning, illegitimate distribution and use. IP protection mechanisms have been applied to AI models, and in particular to deep neural networks, to verify the model ownership. State-of-the-art AI model ownership protection techniques have been surveyed. The pros and cons of AI model ownership protection have been reported. The majority of previous works are focused on watermarking, while more advanced methods such fingerprinting and attestation are promising but not yet explored in depth. This study has been concluded by discussing possible research directions in the area.en
dc.description.sponsorshipScience Foundation Ireland (Grant no.12/RC/2289-P2, Insight Centre for Data Analytics)en
dc.description.statusPeer revieweden
dc.description.versionPublished Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRegazzoni, F., Palmieri, P., Smailbegovic, F., Cammarota, R. and Polian, I. (2021) 'Protecting artificial intelligence IPs: a survey of watermarking and fingerprinting for machine learning', CAAI Transactions on Intelligence Technology, 6(2), pp. 180-191. doi: 10.1049/cit2.12029en
dc.identifier.doi10.1049/cit2.12029en
dc.identifier.eissn2468-2322
dc.identifier.endpage191en
dc.identifier.issued2en
dc.identifier.journaltitleCAAI Transactions on Intelligence Technologyen
dc.identifier.startpage180en
dc.identifier.urihttps://hdl.handle.net/10468/12026
dc.identifier.volume6en
dc.language.isoenen
dc.publisherInstitution of Engineering and Technology (IET)en
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/871738/EU/Cross-layer cognitive optimization tools & methods for the lifecycle support of dependable CPSoS/CPSoSawareen
dc.rights© 2021, the Authors. CAAI Transactions on Intelligence Technology published by John Wiley & Sons Ltd on behalf of the Institution of Engineering and Technology and Chongqing University of Technology. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.en
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en
dc.subjectArtificial intelligenceen
dc.subjectAI modelsen
dc.subjectPiracyen
dc.subjectIP protection mechanismsen
dc.titleProtecting artificial intelligence IPs: a survey of watermarking and fingerprinting for machine learningen
dc.typeArticle (peer-reviewed)en
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
cit2.12029.pdf
Size:
427.88 KB
Format:
Adobe Portable Document Format
Description:
Published Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Journal Articles