Towards Differentially Private Text Representations

06/25/2020
by   Lingjuan Lyu, et al.
0

Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter ϵ on accuracy, and provide enhanced flexibility in choosing randomization probabilities for LDP. Analysis and experiments show that our framework delivers comparable or even better performance than the non-private framework and existing LDP protocols, demonstrating the advantages of our LDP protocol.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/04/2018

Distributed Differential Privacy via Mixnets

We consider the problem of designing scalable, robust protocols for comp...
research
09/17/2020

FLAME: Differentially Private Federated Learning in the Shuffle Model

Differentially private federated learning has been intensively studied. ...
research
08/08/2019

Local Differential Privacy for Deep Learning

Deep learning (DL) is a promising area of machine learning which is beco...
research
07/18/2020

How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning

This paper firstly considers the research problem of fairness in collabo...
research
08/02/2022

Differentially Private Vertical Federated Clustering

In many applications, multiple parties have private data regarding the s...
research
04/06/2021

Differentially Private Histograms in the Shuffle Model from Fake Users

There has been much recent work in the shuffle model of differential pri...
research
10/25/2022

Robustness of Locally Differentially Private Graph Analysis Against Poisoning

Locally differentially private (LDP) graph analysis allows private analy...

Please sign up or login with your details

Forgot password? Click here to reset