Sorry, you need to enable JavaScript to visit this website.

Federated Learning With Local Differential Privacy: Trade-Offs Between Privacy, Utility, and Communication

Citation Author(s):
Muah Kim, Onur Günlü, and Rafael F. Schaefer
Submitted by:
Muah Kim
Last updated:
24 June 2021 - 7:18am
Document Type:
Presentation Slides
Document Year:
Muah Kim
Paper Code:


Federated learning (FL) allows to train a massive amount of data privately due to its decentralized structure. Stochastic gradient descent (SGD) is commonly used for FL due to its good empirical performance, but sensitive user information can still be inferred from weight updates shared during FL iterations. We consider Gaussian mechanisms to preserve local differential privacy (LDP) of user data in the FL model with SGD. The trade-offs between user privacy, global utility, and transmission rate are proved by defining appropriate metrics for FL with LDP. Compared to existing results, the query sensitivity used in LDP is defined as a variable, and a tighter privacy accounting method is applied. The proposed utility bound allows heterogeneous parameters over all users. Our bounds characterize how much utility decreases and transmission rate increases if a stronger privacy regime is targeted. Furthermore, given a target privacy level, our results guarantee a significantly larger utility and a smaller transmission rate as compared to existing privacy accounting methods.

0 users have voted:


The pdf file of the poster used for the poster session.


The slides (.pptx file) used for the recorded presentation.