Zobrazeno 1 - 10
of 126
pro vyhledávání: '"Önen, Melek"'
Autor:
Taiello, Riccardo, Cansiz, Sergen, Vesin, Marc, Cremonesi, Francesco, Innocenti, Lucia, Önen, Melek, Lorenzi, Marco
Deploying federated learning (FL) in real-world scenarios, particularly in healthcare, poses challenges in communication and security. In particular, with respect to the federated aggregation procedure, researchers have been focusing on the study of
Externí odkaz:
http://arxiv.org/abs/2409.00974
Autor:
Ünsal, Ayşe, Önen, Melek
This work inspects a privacy metric based on Chernoff information, \textit{Chernoff differential privacy}, due to its significance in characterization of the optimal classifier's performance. Adversarial classification, as any other classification pr
Externí odkaz:
http://arxiv.org/abs/2403.10307
In this paper, we present a stealthy and effective attack that exposes privacy vulnerabilities in Graph Neural Networks (GNNs) by inferring private links within graph-structured data. Focusing on the inductive setting where new nodes join the graph a
Externí odkaz:
http://arxiv.org/abs/2307.13548
Autor:
Chouchane, Oubaïda, Panariello, Michele, Zari, Oualid, Kerenciler, Ismet, Chihaoui, Imen, Todisco, Massimiliano, Önen, Melek
Over the last decade, the use of Automatic Speaker Verification (ASV) systems has become increasingly widespread in response to the growing need for secure and efficient identity verification methods. The voice data encompasses a wealth of personal i
Externí odkaz:
http://arxiv.org/abs/2307.02135
Autor:
Cremonesi, Francesco, Vesin, Marc, Cansiz, Sergen, Bouillard, Yannick, Balelli, Irene, Innocenti, Lucia, Silva, Santiago, Ayed, Samy-Safwan, Taiello, Riccardo, Kameni, Laetita, Vidal, Richard, Orlhac, Fanny, Nioche, Christophe, Lapel, Nathan, Houis, Bastien, Modzelewski, Romain, Humbert, Olivier, Önen, Melek, Lorenzi, Marco
The real-world implementation of federated learning is complex and requires research and development actions at the crossroad between different domains ranging from data science, to software programming, networking, and security. While today several
Externí odkaz:
http://arxiv.org/abs/2304.12012
Publikováno v:
Medical Image Analysis Medical Image Analysis, Volume 94, May 2024, 103129
Image registration is a key task in medical imaging applications, allowing to represent medical images in a common spatial reference frame. Current approaches to image registration are generally based on the assumption that the content of the images
Externí odkaz:
http://arxiv.org/abs/2205.10120
Publikováno v:
In Medical Image Analysis May 2024 94
Autor:
Ünsal, Ayşe, Önen, Melek
This paper studies the statistical characterization of detecting an adversary who wants to harm some computation such as machine learning models or aggregation by altering the output of a differentially private mechanism in addition to discovering so
Externí odkaz:
http://arxiv.org/abs/2105.05610
In this work, we propose a study on the use of post-quantum cryptographic primitives for the Tor network in order to make it safe in a quantum world. With this aim, the underlying keying material has first been analysed. We observe that breaking the
Externí odkaz:
http://arxiv.org/abs/2001.03418
Autor:
ÜNSAL, AYŞE1 ayse.unsal@eurecom.fr, ÖNEN, MELEK1 melek.onen@eurecom.fr
Publikováno v:
ACM Computing Surveys. Mar2024, Vol. 56 Issue 3, p1-18. 18p.