Privacy Amplification for Federated Learning via User Sampling and Wireless Aggregation

by   Mohamed Seif, et al.

In this paper, we study the problem of federated learning over a wireless channel with user sampling, modeled by a Gaussian multiple access channel, subject to central and local differential privacy (DP/LDP) constraints. It has been shown that the superposition nature of the wireless channel provides a dual benefit of bandwidth efficient gradient aggregation, in conjunction with strong DP guarantees for the users. Specifically, the central DP privacy leakage has been shown to scale as 𝒪(1/K^1/2), where K is the number of users. It has also been shown that user sampling coupled with orthogonal transmission can enhance the central DP privacy leakage with the same scaling behavior. In this work, we show that, by join incorporating both wireless aggregation and user sampling, one can obtain even stronger privacy guarantees. We propose a private wireless gradient aggregation scheme, which relies on independently randomized participation decisions by each user. The central DP leakage of our proposed scheme scales as 𝒪(1/K^3/4). In addition, we show that LDP is also boosted by user sampling. We also present analysis for the convergence rate of the proposed scheme and study the tradeoffs between wireless resources, convergence, and privacy theoretically and empirically for two scenarios when the number of sampled participants are (a) known, or (b) unknown at the parameter server.


page 1

page 2

page 3

page 4


Wireless Federated Learning with Local Differential Privacy

In this paper, we study the problem of federated learning (FL) over a wi...

Differentially Private Federated Learning with Local Regularization and Sparsification

User-level differential privacy (DP) provides certifiable privacy guaran...

Wireless Federated Learning with Limited Communication and Differential Privacy

This paper investigates the role of dimensionality reduction in efficien...

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning

We consider the problem of training a d dimensional model with distribut...

On Differential Privacy for Federated Learning in Wireless Systems with Multiple Base Stations

In this work, we consider a federated learning model in a wireless syste...

Over-the-Air Federated Averaging with Limited Power and Privacy Budgets

To jointly overcome the communication bottleneck and privacy leakage of ...

Mean Estimation Under Heterogeneous Privacy: Some Privacy Can Be Free

Differential Privacy (DP) is a well-established framework to quantify pr...

Please sign up or login with your details

Forgot password? Click here to reset