AdaSTopk: Adaptive federated shuffle model based on differential privacy

MNIST数据库 差别隐私 联合学习 计算机科学 维数(图论) 摄动(天文学) 分布(数学) 人工智能 数据挖掘 深度学习 数学 数学分析 物理 量子力学 纯数学
作者
Qiantao Yang,Xuehui Du,Aodi Liu,Na Wang,Wenjuan Wang,Xiangyu Wu
出处
期刊:Information Sciences [Elsevier BV]
卷期号:642: 119186-119186 被引量:9
标识
DOI:10.1016/j.ins.2023.119186
摘要

The shuffle model is a promising federated learning method, which has the advantages of the high accuracy of central federated learning and the high security of local federated learning. Although the shuffle model can well address the privacy security and model accuracy issues in federated learning, the existing research on shuffle models mainly has the following problems: First, the layers in machine learning models have different ranges of weights, and only some weights are important. Perturbing all weights equally will discard the importance of some weights and affect the accuracy of the model. Second, due to the perturbation of the weights of all clients, the dimension of model aggregation will increase, and the privacy budget will surge. In this paper, an adaptive top-k differential privacy federated shuffle model is proposed to address the above-mentioned issues, which dynamically adjusts the size of top-k iteratively, enabling the client and the shuffler to control the number of weight parameters that add perturbations, ensuring the importance of weights and reducing the privacy budget under the high-dimensional model. It is found when top-k comes to extremes, the security of the model decreases. To overcome this challenge, this paper proposes a double perturbation mechanism of top-k and non-topk with subsampling, which improves the security of the model and further reduces the privacy budget. Under the three data distributions of independent and identical distribution, non-independent and identical distribution, and non-independent and different distribution, experiments are conducted on three datasets, including MNIST, Fashion-MNIST, and CIFAR-10. The experimental results show that the model proposed in this paper achieves good performance and efficiency for privacy protection.
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
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
殷勤的晓夏完成签到,获得积分10
1秒前
cyc完成签到,获得积分10
1秒前
2秒前
why发布了新的文献求助10
2秒前
limengkai发布了新的文献求助10
3秒前
cjh完成签到,获得积分10
3秒前
4秒前
xixi完成签到,获得积分20
4秒前
领导范儿的应助被勤奋梨愁采纳,获得10
6秒前
sls完成签到,获得积分10
6秒前
yh完成签到,获得积分10
8秒前
万能图书馆的应助被Jason采纳,获得30
9秒前
陆豪杰完成签到,获得积分10
10秒前
充电宝的应助被星辰采纳,获得20
10秒前
11秒前
12秒前
12秒前
勤奋梨愁完成签到,获得积分10
12秒前
xixi关注了科研通微信公众号
13秒前
无花果的应助被guoguozhijia158采纳,获得10
13秒前
14秒前
863发布了新的文献求助10
14秒前
slsdianzi完成签到,获得积分10
15秒前
脱羰甲酸发布了新的文献求助10
16秒前
16秒前
16秒前
852的应助被小冰块采纳,获得10
16秒前
zhaoliancheng完成签到,获得积分20
19秒前
大模型的应助被执着的钢笔采纳,获得10
19秒前
Z_xy完成签到,获得积分10
19秒前
20秒前
细心鲂发布了新的文献求助10
21秒前
zhaoliancheng发布了新的文献求助10
21秒前
霞霞子完成签到 ,获得积分10
22秒前
23秒前
万能图书馆的应助被久怨采纳,获得10
24秒前
SONG完成签到,获得积分10
25秒前
Yy完成签到 ,获得积分10
26秒前
博士完成签到 ,获得积分10
27秒前
27秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8188353
求助须知:如何正确求助?哪些是违规求助? 9576169
关于积分的说明 21845860
捐赠科研通 7786410
什么是DOI,文献DOI怎么找? 3435292
关于科研通互助平台的介绍 2559588
邀请新用户注册赠送积分活动 2482235