Reliable federated learning based on dual-reputation reverse auction mechanism in Internet of Things

计算机科学 声誉 信誉制度 计算机安全 激励 机器学习 人工智能 对偶(语法数字) 过程(计算) 质量(理念) 基线(sea) 文学类 地质学 哲学 艺术 社会学 操作系统 经济 微观经济学 认识论 海洋学 社会科学
作者
Y. A. Tang,Yongquan Liang,Yang Liu,Jinquan Zhang,Lina Ni,Liang Qi
出处
期刊:Future Generation Computer Systems [Elsevier BV]
卷期号:156: 269-284 被引量:14
标识
DOI:10.1016/j.future.2024.03.019
摘要

Federated learning, a promising distributed machine learning paradigm, has been used in various Internet of Things (IoT) environments to solve isolated data island issues and protect data privacy. However, since the central server in federated learning cannot detect the local training process of the client, it is vulnerable to adversarial attacks against its security and privacy by malicious clients during the training process. To address this problem, this work proposes a federated learning system model based on dual-reputation reverse auction in IoT. Specifically, due to resource constraints, not all clients participate in the federated learning process, so we propose the reputation-bid ratio based greedy half-splitting algorithm to select some clients to participate in the federated learning, which can guarantee that each client has the chance to be selected while selecting as many honest and high-quality clients as possible. Then, we propose an adaptive dropout aggregation method based on a training quality score, which can effectively defend against malicious workers' attacks. After the completion of federated learning, we put forward a subjective evaluation incentive mechanism based on a second reputation to realize the fair incentive. Furthermore, we store and manage reputations through blockchain in our model to ensure their availability. Theoretical analysis deduces the complexity and security of our proposed model. Finally, simulation results indicate that our proposed model can achieve the highest accuracy across all test datasets compared to the baseline. Particularly, on the CIFAR10 dataset, the accuracy of our proposed model surpasses the baseline by 5% to 30%. In responding to sudden attacks initiated by normally participating workers, our model exhibits the fastest reaction time, with accuracy surpassing the baseline by 8% to 40%.
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
小王发布了新的文献求助10
2秒前
2秒前
3秒前
doudou完成签到,获得积分10
3秒前
麦可完成签到,获得积分10
3秒前
shuangshuang完成签到,获得积分10
3秒前
沐沐1003完成签到,获得积分10
4秒前
拣尽南枝完成签到 ,获得积分10
4秒前
5秒前
ding应助HHEHK采纳,获得10
5秒前
Zzx完成签到,获得积分10
6秒前
Fin2046发布了新的文献求助30
7秒前
炒鸡小将完成签到,获得积分10
7秒前
机智灵薇发布了新的文献求助10
8秒前
8秒前
橙子完成签到 ,获得积分10
9秒前
刻苦的晓蕾完成签到,获得积分10
9秒前
崔志海完成签到,获得积分10
10秒前
10秒前
11秒前
胡须应助祁乐安采纳,获得20
14秒前
刘钱美子完成签到,获得积分10
14秒前
qian完成签到 ,获得积分10
14秒前
李治海发布了新的文献求助10
15秒前
醉眠完成签到 ,获得积分10
15秒前
Fin2046完成签到,获得积分10
15秒前
学不懂数学完成签到,获得积分10
16秒前
莓烦恼完成签到 ,获得积分10
17秒前
18秒前
白江虎完成签到,获得积分10
19秒前
20秒前
阳光的凌雪完成签到 ,获得积分10
21秒前
文艺小馒头完成签到,获得积分10
21秒前
赵赵发布了新的文献求助20
22秒前
橙子发布了新的文献求助10
24秒前
25秒前
Wsyyy完成签到 ,获得积分10
27秒前
27秒前
ganjqly完成签到,获得积分10
27秒前
董惠玲66发布了新的文献求助10
28秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
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 4038303
求助须知:如何正确求助?哪些是违规求助? 3576013
关于积分的说明 11374210
捐赠科研通 3305780
什么是DOI,文献DOI怎么找? 1819322
邀请新用户注册赠送积分活动 892672
科研通“疑难数据库(出版商)”最低求助积分说明 815029