Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Weinert, Christian"'
Autor:
Marx, Felix, Schneider, Thomas, Suresh, Ajith, Wehrle, Tobias, Weinert, Christian, Yalame, Hossein
Federated learning (FL) is an efficient approach for large-scale distributed machine learning that promises data privacy by keeping training data on client devices. However, recent research has uncovered vulnerabilities in FL, impacting both security
Externí odkaz:
http://arxiv.org/abs/2302.09904
Autor:
Ben-Itzhak, Yaniv, Möllering, Helen, Pinkas, Benny, Schneider, Thomas, Suresh, Ajith, Tkachenko, Oleksandr, Vargaftik, Shay, Weinert, Christian, Yalame, Hossein, Yanai, Avishay
Secure aggregation is commonly used in federated learning (FL) to alleviate privacy concerns related to the central aggregator seeing all parameter updates in the clear. Unfortunately, most existing secure aggregation schemes ignore two critical orth
Externí odkaz:
http://arxiv.org/abs/2210.07376
Autor:
Weinert, Christian
Private set intersection (PSI) protocols are cryptographic protocols that allow two parties to securely compute the intersection of their private input sets without disclosing elements outside of the intersection. While this simple functionality turn
Externí odkaz:
https://tuprints.ulb.tu-darmstadt.de/19295/1/Dissertation_ChristianWeinert_010921.pdf
Autor:
Mann, Zoltán Ádám1 (AUTHOR) zoltan.mann@gmail.com, Weinert, Christian2 (AUTHOR) Christian.Weinert@rhul.ac.uk, Chabal, Daphnee1 (AUTHOR) d.n.m.s.chabal@uva.nl, Bos, Joppe W.3 (AUTHOR) joppe.bos@nxp.com
Publikováno v:
ACM Computing Surveys. May2024, Vol. 56 Issue 5, p1-37. 37p.
Autor:
Cammarota, Rosario, Schunter, Matthias, Rajan, Anand, Boemer, Fabian, Kiss, Ágnes, Treiber, Amos, Weinert, Christian, Schneider, Thomas, Stapf, Emmanuel, Sadeghi, Ahmad-Reza, Demmler, Daniel, Stock, Joshua, Chen, Huili, Hussain, Siam Umar, Riazi, Sadegh, Koushanfar, Farinaz, Gupta, Saransh, Rosing, Tajan Simunic, Chaudhuri, Kamalika, Nejatollahi, Hamid, Dutt, Nikil, Imani, Mohsen, Laine, Kim, Dubey, Anuj, Aysu, Aydin, Hosseini, Fateme Sadat, Yang, Chengmo, Wallace, Eric, Norton, Pamela
In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized inferences to
Externí odkaz:
http://arxiv.org/abs/2008.04449
Autor:
Bayerl, Sebastian P., Frassetto, Tommaso, Jauernig, Patrick, Riedhammer, Korbinian, Sadeghi, Ahmad-Reza, Schneider, Thomas, Stapf, Emmanuel, Weinert, Christian
Publikováno v:
DATE 2020, pages 460-465
Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers (e.g., model p
Externí odkaz:
http://arxiv.org/abs/2007.02351
AI algorithms, and machine learning (ML) techniques in particular, are increasingly important to individuals' lives, but have caused a range of privacy concerns addressed by, e.g., the European GDPR. Using cryptographic techniques, it is possible to
Externí odkaz:
http://arxiv.org/abs/2002.00801
Autor:
Riazi, M. Sadegh, Weinert, Christian, Tkachenko, Oleksandr, Songhori, Ebrahim M., Schneider, Thomas, Koushanfar, Farinaz
We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing their private inputs. Chameleon combines the best aspects of generic SFE p
Externí odkaz:
http://arxiv.org/abs/1801.03239
Publikováno v:
ASIACCS 2017, pages 436-448
Current trends in technology, such as cloud computing, allow outsourcing the storage, backup, and archiving of data. This provides efficiency and flexibility, but also poses new risks for data security. It in particular became crucial to develop prot
Externí odkaz:
http://arxiv.org/abs/1708.02091
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.