paper-with-me

Papers

Differentially Private Federated Learning: A Client Level Perspective

2017-12-20 · ICLR 2019 5 · Robin C. Geyer, Tassilo Klein, Moin Nabi

Federated learning is a recent advance in privacy protection. In this context, a trusted curator aggregates parameters optimized in decentralized fashion by multiple clients. The resulting model is then distributed back to all clients, ultimately converging to a joint representative model without explicitly having to share the data. However, the protocol is vulnerable to differential attacks, which could originate from any party contributing during federated optimization. In such an attack, a client's contribution during training and information about their data set is revealed through analyzing the distributed model. We tackle this problem and propose an algorithm for client sided differential privacy preserving federated optimization. The aim is to hide clients' contributions during training, balancing the trade-off between privacy loss and model performance. Empirical studies suggest that given a sufficiently large number of participating clients, our proposed procedure can maintain client-level differential privacy at only a minor cost in model performance.

📄 PDF Abstract BibTeX arXiv:1712.07557

Code (6)

cyrusgeyer/DiffPrivate_FedLearning 공식 구현 tf
KaiyuanZh/censor pytorch
SAP-samples/machine-learning-diff-private-federated-learning tf
SAP/machine-learning-diff-private-federated-learning tf
michelle0924hhx/DiffPrivate_FedLearning tf
sapmlresearch/DiffPrivate_FedLearning tf

Tasks

Federated LearningPrivacy Preserving

Similar Papers 제목 키워드 기반

FedAUXfdp: Differentially Private One-Shot Federated Distillation

2022-05-30 · Haley Hoech, Roman Rischke, Karsten Müller, Wojciech Samek

Federated learning suffers in the case of non-iid local datasets, i.e., when the distributions of the clients' data are heterogeneous. One promising approach to this challenge is the recently proposed method FedAUX, an a…

Federated Learning

Near-optimal Differentially Private Client Selection in Federated Settings

2023-10-13 · Syed Eqbal Alam, Dhirendra Shukla, Shrisha Rao

We develop an iterative differentially private algorithm for client selection in federated settings. We consider a federated network wherein clients coordinate with a central server to complete a task; however, the clien…

Federated Learning in Non-IID Settings Aided by Differentially Private Synthetic Data

2022-06-01 · Huancheng Chen, Haris Vikalo

Federated learning (FL) is a privacy-promoting framework that enables potentially large number of clients to collaboratively train machine learning models. In a FL system, a server coordinates the collaboration by collec…

Federated Learningimage-classificationImage Classification

Differentially Private Federated Variational Inference

2019-11-24 · Mrinank Sharma, Michael Hutchinson, Siddharth Swaroop, Antti Honkela 외

In many real-world applications of machine learning, data are distributed across many clients and cannot leave the devices they are stored on. Furthermore, each client's data, computational resources and communication co…

Bayesian InferenceFederated LearningVariational Inference

FedHypeVAE: Federated Learning with Hypernetwork Generated Conditional VAEs for Differentially Private Embedding Sharing

2026-01-02 · Sunny Gupta, Amit Sethi arxiv

Federated data sharing promises utility without centralizing raw data, yet existing embedding-level generators struggle under non-IID client heterogeneity and provide limited formal protection against gradient leakage. W…

Federated Learning