E2EGI: End-to-End Gradient Inversion in Federated Learning

计算机科学 反演(地质) 深度学习 互联网 人气 性能指标 人工智能 数据挖掘 万维网 心理学 古生物学 社会心理学 构造盆地 经济 生物 管理
作者
Zhaohua Li,Le Wang,Guangyao Chen,Zhiqiang Zhang,Muhammad Shafiq,Zhaoquan Gu
出处
期刊:IEEE Journal of Biomedical and Health Informatics [Institute of Electrical and Electronics Engineers]
卷期号:27 (2): 756-767 被引量:8
标识
DOI:10.1109/jbhi.2022.3204455
摘要

A plethora of healthcare data is produced every day due to the proliferation of prominent technologies such as Internet of Medical Things (IoMT). Digital-driven smart devices like wearable watches, wristbands and bracelets are utilized extensively in modern healthcare applications. Mining valuable information from the data distributed at the owners' level is useful, but it is challenging to preserve data privacy. Federated learning (FL) has swiftly surged in popularity due to its efficacy in dealing privacy vulnerabilities. Recent studies have demonstrated that Gradient Inversion Attack (GIA) can reconstruct the input data by leaked gradients, previous work demonstrated the achievement of GIA in very limited scenarios, such as the label repetition rate of the target sample being low and batch sizes being smaller than 48. In this paper, a novel method of End-to-End Gradient Inversion (E2EGI) is proposed. Compared to the state-of-the-art method, E2EGI's Minimum Loss Combinatorial Optimization (MLCO) has the ability to realize reconstructed samples with higher similarity, and the Distributed Gradient Inversion algorithm can implement GIA with batch sizes of 8 to 256 on deep network models (such as ResNet-50) and ImageNet datasets. A new Label Reconstruction algorithm is developed that relies only on the gradient information of the target model, which can achieve a label reconstruction accuracy of 81% in one batch sample with a label repetition rate of 96%, a 27% improvement over the state-of-the-art method. This proposed work can underpin data security assessments for healthcare federated learning.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Super Zzzz发布了新的文献求助10
1秒前
方法完成签到,获得积分10
1秒前
杨凡发布了新的文献求助10
1秒前
Yoh1220应助吴祥坤采纳,获得50
1秒前
YoungLee完成签到,获得积分10
1秒前
波尔完成签到 ,获得积分10
1秒前
1秒前
AZE应助future采纳,获得10
1秒前
美满的萝发布了新的文献求助10
2秒前
完美世界应助boook采纳,获得10
2秒前
2秒前
kent发布了新的文献求助10
2秒前
3秒前
罗中翠完成签到,获得积分10
3秒前
完美世界应助Xx采纳,获得10
3秒前
Jasper应助含蓄绿兰采纳,获得10
4秒前
4秒前
5秒前
领导范儿应助sdsa采纳,获得10
5秒前
5秒前
粒粒2完成签到 ,获得积分10
5秒前
ganjqly完成签到,获得积分10
6秒前
accept发布了新的文献求助10
6秒前
李健应助miaomiaomiao采纳,获得10
6秒前
6秒前
蛋卷发布了新的文献求助10
6秒前
积极的若山发布了新的文献求助200
6秒前
我是老大应助srui采纳,获得10
7秒前
zmayq完成签到,获得积分10
7秒前
瓜姐发布了新的文献求助10
8秒前
egg完成签到,获得积分10
8秒前
鲤鱼白枫完成签到,获得积分10
9秒前
9秒前
7777发布了新的文献求助10
9秒前
10秒前
11关注了科研通微信公众号
10秒前
10秒前
10秒前
11秒前
Super Zzzz完成签到,获得积分10
11秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
A Preliminary Study on Correlation Between Independent Components of Facial Thermal Images and Subjective Assessment of Chronic Stress 500
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 360
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970802
求助须知:如何正确求助?哪些是违规求助? 3515474
关于积分的说明 11178714
捐赠科研通 3250627
什么是DOI,文献DOI怎么找? 1795390
邀请新用户注册赠送积分活动 875818
科研通“疑难数据库(出版商)”最低求助积分说明 805183