arrow
返回

Multi-Trigger-Key: Toward Multi-Task Privacy Preserving in Deep Learning

delete2024-01-01
delete0
delete
OA
AI
R
Ren Wang *
Z
Zhe Xu
A
Alfred O. Hero *
DOI:10.1109/ACCESS.2024.3360004delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Deep learning-based Multi-Task Classification (MTC) is widely used in applications such as facial attributes and healthcare, which require robust privacy guarantees. In this study, we propose a novel Multi-Trigger-Key (MTK) framework to fulfill the privacy-preservation objective of protecting sensitive information throughout the entire workflow of MTC. We provide two real world examples that demonstrates how MTK can be implemented in the context of healthcare and financial tasks. Each secured task in the multi-task dataset is linked to a specially crafted trigger-key, processed by a data distributor, a secret key distributor, an assembler, and a model optimizer/keeper in the MTK system. If a user is authorized to access certain data, the insertion of trigger keys will reveal the accurate information. Furthermore, the learning process is structured to allow the four MTK agents to collaboratively distribute privacy protection. To address the information leakage problem caused by correlations among different classes, MTK training also includes a tuning parameter, which is used to balance the protective efficacy and model performance. Theoretical assurances and experimental results demonstrate that privacy protection is effective without significantly compromising model performance.
Keyword:
Deep learning
neural network
multi-task
privacy
trigger

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
29.4W

机构

A
Arizona State University
学者数:
2.7W
论文数: 2.5W
被引数: 4.2W
I
Illinois Institute of Technology
学者数:
3.8K
论文数: 3.9K
被引数: 4.2K
A
arizona state university-tempe
学者数:
1.5W
论文数: 1.2W
被引数: 13
学者 查看更多机构
引用论文

引用论文

err分享
err收藏
err
IF0
err
err0
PREAI
err
err分享
err收藏
Clinical significance of PD-L1 and PD-L2 copy number gains in non-small-cell lung cancer
err2016-04-01
err0
errOAAI
errYusuke Inoue; Katsuhiro Yoshimura; Kazutaka Mori; Nobuya Kurabe; Tomoaki Kahyo; Hiroki Mori; Akikazu Kawase; Masayuki Tanahashi; Hiroshi Ogawa; Naoki Inui; Kazuhito Funai; Kazuya Shinmura; Hiroshi Niwa; Takafumi Suda; Haruhiko Sugimura
err分享
err收藏
Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks
err2022-01-01
err10
errOAAI
errMahmood, Kaleel; Mahmood, Rigel; Rathbun, Ethan; van Dijk, Marten
err分享
err收藏
学者 查看更多内容