PATE-AAE: Incorporating Adversarial Autoencoder into Private Aggregation of Teacher Ensembles for Spoken Command Classification

04/02/2021
by   Chao-Han Huck Yang, et al.
0

We propose using an adversarial autoencoder (AAE) to replace generative adversarial network (GAN) in the private aggregation of teacher ensembles (PATE), a solution for ensuring differential privacy in speech applications. The AAE architecture allows us to obtain good synthetic speech leveraging upon a discriminative training of latent vectors. Such synthetic speech is used to build a privacy-preserving classifier when non-sensitive data is not sufficiently available in the public domain. This classifier follows the PATE scheme that uses an ensemble of noisy outputs to label the synthetic samples and guarantee ε-differential privacy (DP) on its derived classifiers. Our proposed framework thus consists of an AAE-based generator and a PATE-based classifier (PATE-AAE). Evaluated on the Google Speech Commands Dataset Version II, the proposed PATE-AAE improves the average classification accuracy by +2.11% and +6.60%, respectively, when compared with alternative privacy-preserving solutions, namely PATE-GAN and DP-GAN, while maintaining a strong level of privacy target at ε=0.01 with a fixed δ=10^-5.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 4

06/21/2019

Scalable Differentially Private Generative Student Model via PATE

Recent rapid development of machine learning is largely due to algorithm...
07/04/2020

RDP-GAN: A Rényi-Differential Privacy based Generative Adversarial Network

Generative adversarial network (GAN) has attracted increasing attention ...
10/04/2019

PPGAN: Privacy-preserving Generative Adversarial Network

Generative Adversarial Network (GAN) and its variants serve as a perfect...
06/05/2019

Private Deep Learning with Teacher Ensembles

Privacy-preserving deep learning is crucial for deploying deep neural ne...
11/27/2021

Towards Understanding the Impact of Model Size on Differential Private Classification

Differential privacy (DP) is an essential technique for privacy-preservi...
01/10/2022

Differentially Private Generative Adversarial Networks with Model Inversion

To protect sensitive data in training a Generative Adversarial Network (...
02/24/2018

Scalable Private Learning with PATE

The rapid adoption of machine learning has increased concerns about the ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.