Unsupervised Domain Adaptation with Differentially Private Gradient Projection

Author:

Zheng Maobo1ORCID,Zhang Xiaojian2,Ma Xuebin1ORCID

Affiliation:

1. Inner Mongolia Key Laboratory of Wireless Networking and Mobile Computing, Inner Mongolia University, Hohhot, China

2. School of Computer & Information Engineering, Henan University of Economics and Law, Zhengzhou, China

Abstract

Domain adaptation is a viable solution for deep learning with small data. However, domain adaptation models trained on data with sensitive information may be a violation of personal privacy. In this article, we proposed a solution for unsupervised domain adaptation, called DP-CUDA, which is based on differentially private gradient projection and contradistinguisher. Compared with the traditional domain adaptation process, DP-CUDA involves searching for domain-invariant features between the source domain and target domain first and then transferring knowledge. Specifically, the model is trained in the source domain by supervised learning from labeled data. During the training of the target model, feature learning is used to solve the classification task in an end-to-end manner using unlabeled data directly, and the differentially private noise is injected into the gradient. We conducted extensive experiments on a variety of benchmark datasets, including MNIST, USPS, SVHN, VisDA-2017, Office-31, and Amazon Review, to demonstrate our proposed method’s utility and privacy-preserving properties.

Funder

Science and Technology Major Project of Inner Mongolia

Publisher

Hindawi Limited

Subject

Artificial Intelligence,Human-Computer Interaction,Theoretical Computer Science,Software

Reference59 articles.

1. Machine learning models that remember too much;C. Song,2017

2. Model inversion attacks that exploit confidence information and basic countermeasures;M. Fredrikson

3. Facebook in privacy breach;E. Steel;The Wall Street Journal,2010

4. Corporate directors’ and officers’ cybersecurity standard of care: the Yahoo data breach;L. J. Trautman;American University Law Review,2016

5. The EU General Data Protection Regulation (GDPR)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3