一种基于Krum AGR的隐私保护鲁棒联邦学习方案

Xiumin Li, Mi Wen, Siying He, Rongxing Lu, Liangliang Wang
{"title":"一种基于Krum AGR的隐私保护鲁棒联邦学习方案","authors":"Xiumin Li, Mi Wen, Siying He, Rongxing Lu, Liangliang Wang","doi":"10.1109/ICCC57788.2023.10233385","DOIUrl":null,"url":null,"abstract":"The sensitive information of participants would be leaked to an untrustworthy server through gradients in federated learning. Encrypted aggregation of uploaded parameters could resolve this issue. However, it brings challenges to the defense of model poisoning attacks in federated learning while solving the privacy problem. To address this issue, a robust federated learning scheme with privacy-preserving (RFLP) is proposed to eliminate the impact of model poisoning attacks while protecting the privacy of participants against untrusted servers. Specifically, an abnormal gradients detecting method is designed to achieve robust federated learning under encrypted aggregation using Pailliar homomorphic encryption. It is based on the concept of Krum aggregation algorithm (AGR), but utilizes privacy-preserving data features, thereby ensuring privacy. To reduce the rounds of communication in robust aggregation, a multidimensional homomorphic encryption approach is constructed. Besides, an aggregated signature authentication method is also constructed to ensure data integrity during transmission. The experiment results show that the training accuracy of RFLP with 10% malicious participants is 11.9% and 15.3% higher than that without robust aggregation.","PeriodicalId":191968,"journal":{"name":"2023 IEEE/CIC International Conference on Communications in China (ICCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Scheme for Robust Federated Learning with Privacy-preserving Based on Krum AGR\",\"authors\":\"Xiumin Li, Mi Wen, Siying He, Rongxing Lu, Liangliang Wang\",\"doi\":\"10.1109/ICCC57788.2023.10233385\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The sensitive information of participants would be leaked to an untrustworthy server through gradients in federated learning. Encrypted aggregation of uploaded parameters could resolve this issue. However, it brings challenges to the defense of model poisoning attacks in federated learning while solving the privacy problem. To address this issue, a robust federated learning scheme with privacy-preserving (RFLP) is proposed to eliminate the impact of model poisoning attacks while protecting the privacy of participants against untrusted servers. Specifically, an abnormal gradients detecting method is designed to achieve robust federated learning under encrypted aggregation using Pailliar homomorphic encryption. It is based on the concept of Krum aggregation algorithm (AGR), but utilizes privacy-preserving data features, thereby ensuring privacy. To reduce the rounds of communication in robust aggregation, a multidimensional homomorphic encryption approach is constructed. Besides, an aggregated signature authentication method is also constructed to ensure data integrity during transmission. The experiment results show that the training accuracy of RFLP with 10% malicious participants is 11.9% and 15.3% higher than that without robust aggregation.\",\"PeriodicalId\":191968,\"journal\":{\"name\":\"2023 IEEE/CIC International Conference on Communications in China (ICCC)\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-08-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/CIC International Conference on Communications in China (ICCC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCC57788.2023.10233385\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/CIC International Conference on Communications in China (ICCC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCC57788.2023.10233385","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在联邦学习中,参与者的敏感信息会通过梯度泄露给不可信的服务器。上传参数的加密聚合可以解决此问题。然而,在解决隐私问题的同时,也给联邦学习中模型中毒攻击的防御带来了挑战。为了解决这一问题,提出了一种具有隐私保护的鲁棒联邦学习方案(RFLP),以消除模型中毒攻击的影响,同时保护参与者的隐私免受不可信服务器的攻击。具体而言,设计了一种异常梯度检测方法,利用paillie同态加密实现加密聚合下的鲁棒联邦学习。它基于Krum聚合算法(AGR)的概念,但利用了保护隐私的数据特征,从而保证了隐私。为了减少鲁棒聚合中的通信轮数,构造了一种多维同态加密方法。此外,还构造了一种聚合签名认证方法,保证数据在传输过程中的完整性。实验结果表明,添加10%恶意参与者时,RFLP的训练准确率比未添加鲁棒聚合时分别提高11.9%和15.3%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A Scheme for Robust Federated Learning with Privacy-preserving Based on Krum AGR
The sensitive information of participants would be leaked to an untrustworthy server through gradients in federated learning. Encrypted aggregation of uploaded parameters could resolve this issue. However, it brings challenges to the defense of model poisoning attacks in federated learning while solving the privacy problem. To address this issue, a robust federated learning scheme with privacy-preserving (RFLP) is proposed to eliminate the impact of model poisoning attacks while protecting the privacy of participants against untrusted servers. Specifically, an abnormal gradients detecting method is designed to achieve robust federated learning under encrypted aggregation using Pailliar homomorphic encryption. It is based on the concept of Krum aggregation algorithm (AGR), but utilizes privacy-preserving data features, thereby ensuring privacy. To reduce the rounds of communication in robust aggregation, a multidimensional homomorphic encryption approach is constructed. Besides, an aggregated signature authentication method is also constructed to ensure data integrity during transmission. The experiment results show that the training accuracy of RFLP with 10% malicious participants is 11.9% and 15.3% higher than that without robust aggregation.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信