Differentially Private Transfer Learning with Conditionally Deep Autoencoders

05/10/2021
by   Mohit Kumar, et al.
0

This paper considers the problem of differentially private semi-supervised transfer learning. The notion of membership-mapping is developed using measure theory basis to learn data representation via a fuzzy membership function. An alternative conception of deep autoencoder, referred to as Conditionally Deep Membership-Mapping Autoencoder (CDMMA) (that consists of a nested compositions of membership-mappings), is considered. Under practice-oriented settings, an analytical solution for the learning of CDMFA can be derived by means of variational optimization. The paper proposes a transfer learning approach that combines CDMMA with a tailored noise adding mechanism to achieve a given level of privacy-loss bound with the minimum perturbation of the data. Numerous experiments were carried out using MNIST, USPS, Office, and Caltech256 datasets to verify the competitive robust performance of the proposed methodology.

READ FULL TEXT

page 20

page 29

research
11/15/2021

Colored Noise Mechanism for Differentially Private Clustering

The goal of this paper is to propose and analyze a differentially privat...
research
03/16/2021

The Influence of Dropout on Membership Inference in Differentially Private Models

Differentially private models seek to protect the privacy of data the mo...
research
10/16/2022

A General Framework for Auditing Differentially Private Machine Learning

We present a framework to statistically audit the privacy guarantee conf...
research
01/29/2019

Representation Transfer for Differentially Private Drug Sensitivity Prediction

Motivation: Human genomic datasets often contain sensitive information t...
research
05/25/2022

Differentially Private Data Generation Needs Better Features

Training even moderately-sized generative models with differentially-pri...
research
05/27/2020

Benchmarking Differentially Private Residual Networks for Medical Imagery

Hospitals and other medical institutions often have vast amounts of medi...
research
06/16/2020

SPEED: Secure, PrivatE, and Efficient Deep learning

This paper addresses the issue of collaborative deep learning with priva...

Please sign up or login with your details

Forgot password? Click here to reset