Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning

Authors: Jinhyun So, Ramy E. Ali, Başak Güler, Jiantao Jiao, A. Salman Avestimehr

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments on MNIST, CIFAR-10 and CIFAR100 datasets in the IID and the non-IID settings demonstrate the performance improvement over the baselines in terms of privacy protection and test accuracy.
Researcher Affiliation Collaboration Jinhyun So*1, Ramy E. Ali 1, Bas ak G uler2, Jiantao Jiao3, A. Salman Avestimehr1 1 University of Southern California (USC) 2 University of California, Riverside 3 University of California, Berkeley jinhyun.so@samsung.com, ramy.ali@samsung.com, bguler@ece.ucr.edu, jiantao@eecs.berkeley.edu, avestime@usc.edu
Pseudocode Yes We describe the two components of Multi-Round Sec Agg in detail in Algorithms 1 and 2 in (So et al. 2021b, App. D).
Open Source Code No The paper does not provide an explicit statement or link for open-source code for the methodology described in this specific version.
Open Datasets Yes MNIST (Le Cun, Cortes, and Burges 2010), CIFAR-10, and CIFAR100 (Krizhevsky and Hinton 2009)
Dataset Splits No The paper describes how training samples are partitioned across users (IID and Non-IID settings) but does not explicitly provide details about train/validation/test dataset splits with percentages or counts.
Hardware Specification No The paper does not specify the hardware (e.g., GPU, CPU models, memory) used for conducting the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes The hyperparameters are provided in (So et al. 2021b, App. F).