Zobrazeno 1 - 10
of 53
pro vyhledávání: '"RAMAGE, DANIEL"'
Autor:
Daly, Katharine, Eichner, Hubert, Kairouz, Peter, McMahan, H. Brendan, Ramage, Daniel, Xu, Zheng
Federated Learning (FL) is a machine learning technique that enables multiple entities to collaboratively learn a shared model without exchanging their local data. Over the past decade, FL systems have achieved substantial progress, scaling to millio
Externí odkaz:
http://arxiv.org/abs/2410.08892
Autor:
Bagdasarian, Eugene, Yi, Ren, Ghalebikesabi, Sahra, Kairouz, Peter, Gruteser, Marco, Oh, Sewoong, Balle, Borja, Ramage, Daniel
The growing use of large language model (LLM)-based conversational agents to manage sensitive user data raises significant privacy concerns. While these agents excel at understanding and acting on context, this capability can be exploited by maliciou
Externí odkaz:
http://arxiv.org/abs/2405.05175
Autor:
Eichner, Hubert, Ramage, Daniel, Bonawitz, Kallista, Huba, Dzmitry, Santoro, Tiziano, McLarnon, Brett, Van Overveldt, Timon, Fallen, Nova, Kairouz, Peter, Cheu, Albert, Daly, Katharine, Gascon, Adria, Gruteser, Marco, McMahan, Brendan
Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization mechanisms like d
Externí odkaz:
http://arxiv.org/abs/2404.10764
Pre-training on public data is an effective method to improve the performance for federated learning (FL) with differential privacy (DP). This paper investigates how large language models (LLMs) trained on public data can improve the quality of pre-t
Externí odkaz:
http://arxiv.org/abs/2404.04360
This white paper describes recent advances in Gboard(Google Keyboard)'s use of federated learning, DP-Follow-the-Regularized-Leader (DP-FTRL) algorithm, and secure aggregation techniques to train machine learning (ML) models for suggestion, predictio
Externí odkaz:
http://arxiv.org/abs/2306.14793
While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not fully understood. In this work, we aim to develop a comprehensive systemiz
Externí odkaz:
http://arxiv.org/abs/2108.10241
Research on the development of science has focused on the creation of multidisciplinary teams. However, while this coming together of people is symmetrical, the ideas, methods, and vocabulary of science have a directional flow. We present a statistic
Externí odkaz:
http://arxiv.org/abs/2004.01291
Autor:
Kairouz, Peter, McMahan, H. Brendan, Avent, Brendan, Bellet, Aurélien, Bennis, Mehdi, Bhagoji, Arjun Nitin, Bonawitz, Kallista, Charles, Zachary, Cormode, Graham, Cummings, Rachel, D'Oliveira, Rafael G. L., Eichner, Hubert, Rouayheb, Salim El, Evans, David, Gardner, Josh, Garrett, Zachary, Gascón, Adrià, Ghazi, Badih, Gibbons, Phillip B., Gruteser, Marco, Harchaoui, Zaid, He, Chaoyang, He, Lie, Huo, Zhouyuan, Hutchinson, Ben, Hsu, Justin, Jaggi, Martin, Javidi, Tara, Joshi, Gauri, Khodak, Mikhail, Konečný, Jakub, Korolova, Aleksandra, Koushanfar, Farinaz, Koyejo, Sanmi, Lepoint, Tancrède, Liu, Yang, Mittal, Prateek, Mohri, Mehryar, Nock, Richard, Özgür, Ayfer, Pagh, Rasmus, Raykova, Mariana, Qi, Hang, Ramage, Daniel, Raskar, Ramesh, Song, Dawn, Song, Weikang, Stich, Sebastian U., Sun, Ziteng, Suresh, Ananda Theertha, Tramèr, Florian, Vepakomma, Praneeth, Wang, Jianyu, Xiong, Li, Xu, Zheng, Yang, Qiang, Yu, Felix X., Yu, Han, Zhao, Sen
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data d
Externí odkaz:
http://arxiv.org/abs/1912.04977
Autor:
Augenstein, Sean, McMahan, H. Brendan, Ramage, Daniel, Ramaswamy, Swaroop, Kairouz, Peter, Chen, Mingqing, Mathews, Rajiv, Arcas, Blaise Aguera y
To improve real-world applications of machine learning, experienced modelers develop intuition about their datasets, their models, and how the two interact. Manual inspection of raw data - of representative samples, of outliers, of misclassifications
Externí odkaz:
http://arxiv.org/abs/1911.06679
Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility. The classical definition of LDP assumes that all elements in the data domain are equally sensitive.
Externí odkaz:
http://arxiv.org/abs/1911.00038