Local Differential Privacy for Deep Learning

08/08/2019
by   M. A. P. Chamikara, et al.
0

Deep learning (DL) is a promising area of machine learning which is becoming popular due to its remarkable accuracy when trained with a massive amount of data. Often, these datasets are highly sensitive crowd-sourced data such as medical data, financial data, or image data, and the DL models trained on these data tend to leak privacy. We propose a new local differentially private (LDP) algorithm (named LATENT) which redesigns the training process in a way that a data owner can add a randomization layer before data leave data owners' devices and reach to a potentially untrusted machine learning service. This way LATENT prevents privacy leaks of DL models, e.g., due to membership inference and memorizing model attacks, while providing excellent accuracy. By not requiring a trusted party, LATENT can be more practical for cloud-based machine learning services in comparison to existing differentially private approaches. Our experimental evaluation of LATENT on convolutional deep neural networks demonstrates excellent accuracy (e.g. 91%- 96%) with high model quality even under very low privacy budgets (e.g. ϵ=0.5), outperforming existing differentially private approaches for deep learning.

READ FULL TEXT
research
05/18/2023

Learning Differentially Private Probabilistic Models for Privacy-Preserving Image Generation

A number of deep models trained on high-quality and valuable images have...
research
02/07/2022

Locally Differentially Private Distributed Deep Learning via Knowledge Distillation

Deep learning often requires a large amount of data. In real-world appli...
research
11/23/2020

Differentially Private Learning Needs Better Features (or Much More Data)

We demonstrate that differentially private machine learning has not yet ...
research
06/25/2020

Towards Differentially Private Text Representations

Most deep learning frameworks require users to pool their local data or ...
research
06/16/2020

SPEED: Secure, PrivatE, and Efficient Deep learning

This paper addresses the issue of collaborative deep learning with priva...
research
05/25/2023

Differentially Private Latent Diffusion Models

Diffusion models (DMs) are widely used for generating high-quality image...
research
11/25/2018

A Fully Private Pipeline for Deep Learning on Electronic Health Records

We introduce an end-to-end private deep learning framework, applied to t...

Please sign up or login with your details

Forgot password? Click here to reset