Výsledky vyhledávání - "Martin Zuber"

Efficient homomorphic evaluation of k-NN classifiers

Autor: Martin Zuber, Renaud Sirdey

Publikováno v: Proceedings on Privacy Enhancing Technologies, Vol 2021, Iss 2, Pp 111-129 (2021)

We design and implement an efficient, secure, homomorphic k-Nearest Neighbours determination algorithm, to be used for regression or classification over private data. Our algorithm runs in quadratic complexity with regard to the size of the database

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::957b3ad17c4f0c0c7e731da640287b52
https://doaj.org/article/b1d12726a35a4878a133b101b83fac2a

Zobrazit plný text záznamu

A Secure Federated Learning: Analysis of Different Cryptographic Tools

Autor: Oana Stan, Vincent Thouvenot, Aymen Boudguiga, Katarzyna Kapusta, Martin Zuber, Renaud Sirdey

Publikováno v: Proceedings of the 19th International Conference on Security and Cryptography.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::9411c7aa1e5b291ab201470a50f21546
https://doi.org/10.5220/0011322700003283

Zobrazit plný text záznamu

Actes de la conférence CAID 2021 (Conference on Artificial Intelligence for Defense)

Autor: Alexandre Dey, Benjamin Costé, Éric Totel, Adrien Bécue, Elkin Aguas, Anthony Lambert, Gregory Blanc, Hervé Debar, Yannick Chevalier, Amine Medad, Baptiste Gregorutti, Edouard Genetay, Alexandre Peter Nguema, Grégoire Menguy, Sébastien Bardin, Richard Bonichon, Cauim de de Souza Lima, Rémy Charayron, Thierry Lefèvre, Nathalie Bartoli, Joseph Morlier, Zakaria Chihani, Bruno Carron, Stephan Brunessaux, Léonard Caquot, Tristan Charrier, Badre El Bezzaz Semlali, Oudomsack Pierre Pasquero, Alexis Bazin, Pierre-Elisée Flory, Katarzyna Kapusta, Oana Stan, Vincent Thouvenot, Karel Hynek, Romain Ferrari, Aimen Boudguiga, Renaud Sirdey, Alice Héliou, Thomas Cejka, Daria La Rocca, Martin Zuber, George Vardoulias, Ioannis Papaioannou, Andreas Vekinis, Georgia Papadopoulou, Marc Vincent, Amal El Fallah-Seghrouchni, Vincent Corruble, Narayan Bernardin, Rami Kassab, Frédéric Barbaresco, Karim Tit, Teddy Furon, Mathias Rousset, Louis-Marie Traonouez, Pierre-Yves Lagrave, Vincent Vidal, Marie-Caroline Corbineau, Tugdual Ceillier, Aleksei Iancheruk, Ahmed Allali, Julien Rodriguez, Tejas Bhor, Ricardo Garcia, Jean-Eudes Guilhot-Gaudeffroy, Robert Plana

Publikováno v: pp.1-152, 2021
HAL

6th European Cyber Week (6ème semaine européenne de la cybersécurité et de la cyberdéfense)

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::f7dfc118ffb956c27559ee25e9520267
https://hal.science/hal-03535661

Zobrazit plný text záznamu

BFV, CKKS, TFHE: Which One is the Best for a Secure Neural Network Evaluation in the Cloud?

Autor: Oana Stan, Pierre-Emmanuel Clet, Martin Zuber

Publikováno v: Lecture Notes in Computer Science ISBN: 9783030816445
ACNS Workshops

We provide clear and concise guidelines for the use of three of the most popular homomorphic cryptosystems: BFV, CKKS and TFHE. Because they are unified under the Chimera framework and it is now possible to switch a ciphertext from one cryptosystem t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6a5779633fe56e070d7cacc841d3dd45
https://doi.org/10.1007/978-3-030-81645-2_16

Zobrazit plný text záznamu

Towards Real-Time Hidden Speaker Recognition by Means of Fully Homomorphic Encryption

Autor: Renaud Sirdey, Sergiu Carpov, Martin Zuber

Publikováno v: Information and Communications Security ISBN: 9783030610777
ICICS

Securing Neural Network (NN) computations through the use of Fully Homomorphic Encryption (FHE) is the subject of a growing interest in both communities. Among different possible approaches to that topic, our work focuses on applying FHE to hide the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::a866eb163d8185aab4e028833516dd98
https://doi.org/10.1007/978-3-030-61078-4_23

Zobrazit plný text záznamu

SPEED: Secure, PrivatE, and Efficient Deep learning

Autor: Cédric Gouy-Pailler, Arnaud Grivet Sébert, Rafael Pinot, Martin Zuber, Renaud Sirdey

Publikováno v: ECML PKDD 2021-European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases
ECML PKDD 2021-European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Basque Center for Applied Mathematics, Sep 2021, Bilbao, Spain. pp.675-694, ⟨10.1007/s10994-021-05970-3⟩

We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning against a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f3dfda1aa6eb6d99d356134d3a63378e

Zobrazit plný text záznamu

Desorption Resistance of Polycyclic Aromatic Hydrocarbons in Biochars Incubated in Cow Ruminal Liquid in Vitro and in Vivo

Autor: Yves Arrigo, Martin Zuber, Isabel Hilber, Thomas D. Bucheli

Publikováno v: Environmental sciencetechnology. 53(23)

Biochar is a new, promising, and sustainable feed additive alternative in agricultural production, which may, however, contain a considerable amount of polycyclic aromatic hydrocarbons (PAHs). As a measure of their bioaccessibility to ruminants, we q

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cf3563f493cd03ec983b58185ab76725
https://pubmed.ncbi.nlm.nih.gov/31682112

Zobrazit plný text záznamu

Practical Fully Homomorphic Encryption for Fully Masked Neural Networks

Autor: Malika Izabachène, Renaud Sirdey, Martin Zuber

Publikováno v: Cryptology and Network Security ISBN: 9783030315771
CANS

Machine learning applications are spreading in many fields and more often than not manipulate private data in order to derive classifications impacting the lives of many individuals. In this context, it becomes important to work on privacy preserving

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::492e7a6390375ea49a36a95a3995fccb
https://doi.org/10.1007/978-3-030-31578-8_2

Zobrazit plný text záznamu

Delay-based priority queueing for VoIP over Software Defined Networks

Autor: Cristian Olariu, Christina Thorpe, Martin Zuber

Publikováno v: IM

Software Defined Networking and Network Function Virtualisation provide significantly more flexibility and control when provisioning QoS for delay sensitive services. Network delay can have a detrimental impact on VoIP quality and, therefore, minimis

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::aeaa0948433991ed349407063fbad6f5
https://doi.org/10.23919/inm.2017.7987352

Zobrazit plný text záznamu

Towards a tight integration of a functional web client language into Scala

Autor: Martin Zuber, Christoph Höger

Publikováno v: SCALA@ECOOP

The web has become an application platform. Therefore it is essential to bring the expressiveness and safety of established languages into the world of web development.Yet it seems hard if not impossible for any such language to succeed over JavaScri

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b6f3829a62c6d703b91246445573c7ac
https://doi.org/10.1145/2489837.2489843

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání