Enhancing the Privacy of Federated Learning with Sketching

11/05/2019
by   Zaoxing Liu, et al.
0

In response to growing concerns about user privacy, federated learning has emerged as a promising tool to train statistical models over networks of devices while keeping data localized. Federated learning methods run training tasks directly on user devices and do not share the raw user data with third parties. However, current methods still share model updates, which may contain private information (e.g., one's weight and height), during the training process. Existing efforts that aim to improve the privacy of federated learning make compromises in one or more of the following key areas: performance (particularly communication cost), accuracy, or privacy. To better optimize these trade-offs, we propose that sketching algorithms have a unique advantage in that they can provide both privacy and performance benefits while maintaining accuracy. We evaluate the feasibility of sketching-based federated learning with a prototype on three representative learning models. Our initial findings show that it is possible to provide strong privacy guarantees for federated learning without sacrificing performance or accuracy. Our work highlights that there exists a fundamental connection between privacy and communication in distributed settings, and suggests important open problems surrounding the theoretical understanding, methodology, and system design of practical, private federated learning.

READ FULL TEXT
research
10/06/2021

Efficient and Private Federated Learning with Partially Trainable Networks

Federated learning is used for decentralized training of machine learnin...
research
11/11/2019

Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices

Federated Learning enables training of a general model through edge devi...
research
12/08/2018

No Peek: A Survey of private distributed deep learning

We survey distributed deep learning models for training or inference wit...
research
11/14/2022

Federated Learning for Appearance-based Gaze Estimation in the Wild

Gaze estimation methods have significantly matured in recent years, but ...
research
06/24/2022

"You Can't Fix What You Can't Measure": Privately Measuring Demographic Performance Disparities in Federated Learning

Federated learning allows many devices to collaborate in the training of...
research
09/03/2023

Federated Few-shot Learning for Cough Classification with Edge Devices

Automatically classifying cough sounds is one of the most critical tasks...

Please sign up or login with your details

Forgot password? Click here to reset