Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Raynal, Mathilde"'
Autor:
Raynal, Mathilde, Troncoso, Carmela
Collaborative Machine Learning (CML) allows participants to jointly train a machine learning model while keeping their training data private. In many scenarios where CML is seen as the solution to privacy issues, such as health-related applications,
Externí odkaz:
http://arxiv.org/abs/2402.13700
Decentralized Learning (DL) is a peer--to--peer learning approach that allows a group of users to jointly train a machine learning model. To ensure correctness, DL should be robust, i.e., Byzantine users must not be able to tamper with the result of
Externí odkaz:
http://arxiv.org/abs/2303.03829
We introduce Private Collection Matching (PCM) problems, in which a client aims to determine whether a collection of sets owned by a server matches their interests. Existing privacy-preserving cryptographic primitives cannot solve PCM problems effici
Externí odkaz:
http://arxiv.org/abs/2206.07009
In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning -- a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both pa
Externí odkaz:
http://arxiv.org/abs/2205.08443
Privacy becomes a crucial issue when outsourcing the training of machine learning (ML) models to cloud-based platforms offering machine-learning services. While solutions based on cryptographic primitives have been developed, they incur a significant
Externí odkaz:
http://arxiv.org/abs/2010.10139
Publikováno v:
Proceedings on Privacy Enhancing Technologies. 2023:446-468
We introduce Private Collection Matching (PCM) problems, in which a client aims to determine whether a collection of sets owned by a server matches their interests. Existing privacy-preserving cryptographic primitives cannot solve PCM problems effici
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5ffb6f05ff50c26df8c7504fa38d696e
https://doi.org/10.56553/popets-2023-0091
https://doi.org/10.56553/popets-2023-0091
Autor:
Paterson, Kenneth G., Raynal, Mathilde
Publikováno v:
2022 IEEE 7th European Symposium on Security and Privacy (EuroS&P)
Computing the count of distinct elements in large data sets is a common task but naive approaches are memory-expensive. The HyperLogLog (HLL) algorithm (Flajolet et al., 2007) estimates a data set's cardinality while using significantly less memory t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bb9e351582c46152c5e9aa812b6e4e03
Autor:
Tauran, Thierry, Raynal, Mathilde
Publikováno v:
Revue de Droit Rural
Revue de Droit Rural, Editions techniques et économiques / LexisNexis (en ligne), 2018, pp.27-30
Revue de Droit Rural, Editions techniques et économiques / LexisNexis (en ligne), 2018, pp.27-30
International audience
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::abdb296baaae113223a8dfe175a554a5
https://hal.univ-lorraine.fr/hal-02400699
https://hal.univ-lorraine.fr/hal-02400699
Autor:
Wilske, Stephan1 stephan.wilske@gleisslutz.com, Raynal, Mathilde2 mathilde.raynal-gng@gleisslutz.com
Publikováno v:
Arbitration International. Sep2021, Vol. 37 Issue 3, p785-791. 7p.
Autor:
Wilske, Stephan, Raynal, Mathilde
Publikováno v:
Dispute Resolution International; May2021, Vol. 15 Issue 1, p199-201, 3p