Federated Learning with Bayesian Differential Privacy

11/22/2019
by   Aleksei Triastcyn, et al.
0

We consider the problem of reinforcing federated learning with formal privacy guarantees. We propose to employ Bayesian differential privacy, a relaxation of differential privacy for similarly distributed data, to provide sharper privacy loss bounds. We adapt the Bayesian privacy accounting method to the federated setting and suggest multiple improvements for more efficient privacy budgeting at different levels. Our experiments show significant advantage over the state-of-the-art differential privacy bounds for federated learning on image classification tasks, including a medical application, bringing the privacy budget below 1 at the client level, and below 0.1 at the instance level. Lower amounts of noise also benefit the model accuracy and reduce the number of communication rounds.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/30/2023

Vision Through the Veil: Differential Privacy in Federated Learning for Medical Image Classification

The proliferation of deep learning applications in healthcare calls for ...
research
05/14/2020

Federated Recommendation System via Differential Privacy

In this paper, we are interested in what we term the federated private b...
research
08/30/2021

Private Multi-Task Learning: Formulation and Applications to Federated Learning

Many problems in machine learning rely on multi-task learning (MTL), in ...
research
12/26/2022

LOCKS: User Differentially Private and Federated Optimal Client Sampling

With changes in privacy laws, there is often a hard requirement for clie...
research
07/16/2022

Sotto Voce: Federated Speech Recognition with Differential Privacy Guarantees

Speech data is expensive to collect, and incredibly sensitive to its sou...
research
10/22/2022

Federated Calibration and Evaluation of Binary Classifiers

We address two major obstacles to practical use of supervised classifier...

Please sign up or login with your details

Forgot password? Click here to reset