Zobrazeno 1 - 10
of 64
pro vyhledávání: '"ElKordy, Ahmed"'
Autor:
Babakniya, Sara, Elkordy, Ahmed Roushdy, Ezzeldin, Yahya H., Liu, Qingfeng, Song, Kee-Bong, El-Khamy, Mostafa, Avestimehr, Salman
Transfer learning via fine-tuning pre-trained transformer models has gained significant success in delivering state-of-the-art results across various NLP tasks. In the absence of centralized data, Federated Learning (FL) can benefit from distributed
Externí odkaz:
http://arxiv.org/abs/2308.06522
Autor:
Zhao, Joshua C., Elkordy, Ahmed Roushdy, Sharma, Atul, Ezzeldin, Yahya H., Avestimehr, Salman, Bagchi, Saurabh
Secure aggregation promises a heightened level of privacy in federated learning, maintaining that a server only has access to a decrypted aggregate update. Within this setting, linear layer leakage methods are the only data reconstruction attacks abl
Externí odkaz:
http://arxiv.org/abs/2303.14868
Autor:
Zhao, Joshua C., Sharma, Atul, Elkordy, Ahmed Roushdy, Ezzeldin, Yahya H., Avestimehr, Salman, Bagchi, Saurabh
Federated learning was introduced to enable machine learning over large decentralized datasets while promising privacy by eliminating the need for data sharing. Despite this, prior work has shown that shared gradients often contain private informatio
Externí odkaz:
http://arxiv.org/abs/2303.12233
Autor:
Elkordy, Ahmed Roushdy, Ezzeldin, Yahya H., Han, Shanshan, Sharma, Shantanu, He, Chaoyang, Mehrotra, Sharad, Avestimehr, Salman
Publikováno v:
APSIPA Transactions on Signal and Information Processing, Volume 12, Issue 1, 2023
Federated analytics (FA) is a privacy-preserving framework for computing data analytics over multiple remote parties (e.g., mobile devices) or silo-ed institutional entities (e.g., hospitals, banks) without sharing the data among parties. Motivated b
Externí odkaz:
http://arxiv.org/abs/2302.01326
Autor:
Elkordy, Ahmed Roushdy, Zhang, Jiang, Ezzeldin, Yahya H., Psounis, Konstantinos, Avestimehr, Salman
Federated learning (FL) has attracted growing interest for enabling privacy-preserving machine learning on data stored at multiple users while avoiding moving the data off-device. However, while data never leaves users' devices, privacy still cannot
Externí odkaz:
http://arxiv.org/abs/2208.02304
Detection and mitigation of Byzantine behaviors in a decentralized learning setting is a daunting task, especially when the data distribution at the users is heterogeneous. As our main contribution, we propose Basil, a fast and computationally effici
Externí odkaz:
http://arxiv.org/abs/2109.07706
Autor:
Abdel-Maged, Amany E., Mikhaeil, Margrit F., Elkordy, Ahmed I., Gad, Amany M., Elshazly, Mohamed M.
Publikováno v:
In Regulatory Toxicology and Pharmacology May 2024 149
Secure model aggregation across many users is a key component of federated learning systems. The state-of-the-art protocols for secure model aggregation, which are based on additive masking, require all users to quantize their model updates to the sa
Externí odkaz:
http://arxiv.org/abs/2009.14388
Autor:
Xu, Xuehong, Naqinezhad, Alireza, Ghazanfar, Shahina A., Fragman-Sapir, Ori, Oganesian, Marine, Dagher Kharrat, Magda Bou, Taifour, Hatem, Filimban, Faten Z., Matchutadze, Izolda, Shavvon, Robabeh Shahi, Abdullah, Mansour T., Al-Khulaidi, Abdul Wali, Al-Issai, Ghudaina, Hussein Al-Newani, Hadeel Radawi, Asswad, Nabegh Ghazal, Chepinoga, Victor V., Homer Eliades, Nicolas-George, Elkordy, Ahmed, Farzaliyev, Vahid, Liu, Yi, Niu, Shukui, Özcan, Taner, Al Sadat, Hounada, Seyfullayev, Farid, Ma, Keping
Publikováno v:
In Global Ecology and Conservation December 2020 24
Publikováno v:
In Review of Palaeobotany and Palynology August 2020 279