no code implementations • 6 May 2024 • Jiang Zhang, Yahya H Ezzeldin, Ahmed Roushdy Elkordy, Konstantinos Psounis, Salman Avestimehr
However, we further demonstrate that in practice, these conditions are almost unlikely to hold and hence additional noise added in model updates is still required in order for SA in FL to achieve DP.
no code implementations • 12 Aug 2023 • Sara Babakniya, Ahmed Roushdy Elkordy, Yahya H. Ezzeldin, Qingfeng Liu, Kee-Bong Song, Mostafa El-Khamy, Salman Avestimehr
In the absence of centralized data, Federated Learning (FL) can benefit from distributed and private data of the FL edge clients for fine-tuning.
no code implementations • CVPR 2023 • Joshua C. Zhao, Ahmed Roushdy Elkordy, Atul Sharma, Yahya H. Ezzeldin, Salman Avestimehr, Saurabh Bagchi
We show that this resource overhead is caused by an incorrect perspective in all prior work that treats an attack on an aggregate update in the same way as an individual update with a larger batch size.
1 code implementation • 21 Mar 2023 • Joshua C. Zhao, Atul Sharma, Ahmed Roushdy Elkordy, Yahya H. Ezzeldin, Salman Avestimehr, Saurabh Bagchi
When both FedAVG and secure aggregation are used, there is no current method that is able to attack multiple clients concurrently in a federated learning setting.
no code implementations • 2 Feb 2023 • Ahmed Roushdy Elkordy, Yahya H. Ezzeldin, Shanshan Han, Shantanu Sharma, Chaoyang He, Sharad Mehrotra, Salman Avestimehr
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.
no code implementations • 3 Aug 2022 • Ahmed Roushdy Elkordy, Jiang Zhang, Yahya H. Ezzeldin, Konstantinos Psounis, Salman Avestimehr
While SA ensures no additional information is leaked about the individual model update beyond the aggregated model update, there are no formal guarantees on how much privacy FL with SA can actually offer; as information about the individual dataset can still potentially leak through the aggregated model computed at the server.
no code implementations • 16 Sep 2021 • Ahmed Roushdy Elkordy, Saurav Prakash, A. Salman Avestimehr
As our main contribution, we propose Basil, a fast and computationally efficient Byzantine robust algorithm for decentralized training systems, which leverages a novel sequential, memory assisted and performance-based criteria for training over a logical ring while filtering the Byzantine users.
no code implementations • 30 Sep 2020 • Ahmed Roushdy Elkordy, A. Salman Avestimehr
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 same level of quantization.
Information Theory Systems and Control Systems and Control Information Theory