Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Maarten Everts"'
Autor:
Federico Mazzone, Leander van den Heuvel, Maximilian Huber, Cristian Verdecchia, Maarten Everts, Florian Hahn, Andreas Peter
Publikováno v:
AISec 2022-Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2022, 13-24
STARTPAGE=13;ENDPAGE=24;TITLE=AISec 2022-Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2022
STARTPAGE=13;ENDPAGE=24;TITLE=AISec 2022-Proceedings of the 15th ACM Workshop on Artificial Intelligence and Security, co-located with CCS 2022
Machine learning models are often trained on sensitive data, such as medical records or bank transactions, posing high privacy risks. In fact, membership inference attacks can use the model parameters or predictions to determine whether a given data
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::29b6cf02c349b77dd18b80c835645231
https://research.utwente.nl/en/publications/5e781644-1731-4856-97b3-9ef9ba6434d2
https://research.utwente.nl/en/publications/5e781644-1731-4856-97b3-9ef9ba6434d2
Publikováno v:
2022 19th Annual International Conference on Privacy, Security and Trust, PST 2022
2022 19th Annual International Conference on Privacy, Security & Trust (PST)
2022 19th Annual International Conference on Privacy, Security & Trust (PST)
In this paper we propose and implement a digital permissioned decentralized anonymous payment scheme that finds a balance between anonymity and auditability. This approach allows banks to ensure that their clients are not participating in illegal fin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8aed1e18e5fb45a1abd9e939f5f1359c
https://doi.org/10.1109/PST55820.2022.9851987
https://doi.org/10.1109/PST55820.2022.9851987