Federated $f$-Differential Privacy

Abstract

Federated learning (FL) is a training paradigm where the clients collaboratively learn models by repeatedly sharing information without compromising much on the privacy of their local sensitive data. In this paper, we introduce federated $f$-differential privacy, a new notion specifically tailored to the federated setting, based on the framework of Gaussian differential privacy. Federated $f$-differential privacy operates on record level: it provides the privacy guarantee on each individual record of one client's data against adversaries. We then propose a generic private federated learning framework {PriFedSync} that accommodates a large family of state-of-the-art FL algorithms, which provably achieves federated $f$-differential privacy. Finally, we empirically demonstrate the trade-off between privacy guarantee and prediction performance for models trained by {PriFedSync} in computer vision tasks.

arXiv commentAccepted to AISTATS 2021

References in corpus (14)

• Adam: A Method for Stochastic Optimization
• Deep Learning with Differential Privacy
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Renyi Differential Privacy
• Learning Differentially Private Recurrent Language Models
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• Differentially Private Federated Learning: A Client Level Perspective
• Federated Optimization in Heterogeneous Networks
• Adaptive Personalized Federated Learning
• Federated Learning of a Mixture of Global and Local Models
• Personalized Federated Learning with Moreau Envelopes
• Hypothesis Testing Interpretations and Renyi Differential Privacy
• Differentially Private Meta-Learning

Cited by in corpus (2)

• The More, the Better? A Study on Collaborative Machine Learning for DGA Detection
• A Communication-efficient Local Differentially Private Algorithm in Federated Optimization