paper-with-me

홈 › Papers

ALI-DPFL: Differentially Private Federated Learning with Adaptive Local Iterations

2023-08-21 · XinPeng Ling, Jie Fu, Kuncan Wang, Haitao Liu, Zhili Chen

Federated Learning (FL) is a distributed machine learning technique that allows model training among multiple devices or organizations by sharing training parameters instead of raw data. However, adversaries can still infer individual information through inference attacks (e.g. differential attacks) on these training parameters. As a result, Differential Privacy (DP) has been widely used in FL to prevent such attacks. We consider differentially private federated learning in a resource-constrained scenario, where both privacy budget and communication rounds are constrained. By theoretically analyzing the convergence, we can find the optimal number of local DPSGD iterations for clients between any two sequential global updates. Based on this, we design an algorithm of Differentially Private Federated Learning with Adaptive Local Iterations (ALI-DPFL). We experiment our algorithm on the MNIST, FashionMNIST and Cifar10 datasets, and demonstrate significantly better performances than previous work in the resource-constraint scenario. Code is available at https://github.com/cheng-t/ALI-DPFL.

📄 PDF Abstract BibTeX arXiv:2308.10457

Code (1)

cheng-t/ali-dpfl 공식 구현 mindspore

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Voting-based Approaches For Differentially Private Federated Learning

2020-10-09 · Yuqing Zhu, Xiang Yu, Yi-Hsuan Tsai, Francesco Pittaluga 외

Differentially Private Federated Learning (DPFL) is an emerging field with many applications. Gradient averaging based DPFL methods require costly communication rounds and hardly work with large-capacity models, due to t…

Federated LearningTransfer Learning

Make Landscape Flatter in Differentially Private Federated Learning

2023-03-20 · CVPR 2023 1 · Yifan Shi, Yingqi Liu, Kang Wei, Li Shen 외

To defend the inference attacks and mitigate the sensitive information leakages in Federated Learning (FL), client-level Differentially Private FL (DPFL) is the de-facto standard for privacy protection by clipping local …

Federated Learning

DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization

2024-09-20 · Zhenxiao Zhang, Yuanxiong Guo, Yanmin Gong

Federated learning (FL) is a distributed machine learning approach that allows multiple clients to collaboratively train a model without sharing their raw data. To prevent sensitive information from being inferred throug…

Federated LearningPersonalized Federated Learning

Mitigating Noise Detriment in Differentially Private Federated Learning with Model Pre-training

2024-08-18 · Huitong Jin, Yipeng Zhou, Laizhong Cui, Quan Z. Sheng

Pre-training exploits public datasets to pre-train an advanced machine learning model, so that the model can be easily tuned to adapt to various downstream tasks. Pre-training has been extensively explored to mitigate co…

Federated Learning

DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm

2025-10-31 · Junkang Liu, Yuxuan Tian, Fanhua Shang, Yuanyuan Liu 외 arxiv

To prevent inference attacks in Federated Learning (FL) and reduce the leakage of sensitive information, Client-level Differentially Private Federated Learning (CL-DPFL) is widely used. However, current CL-DPFL methods u…

Federated Learning