清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

CareFL: C ontribution Guided Byz a ntine- R obust F e derated Learning

计算机科学 Byzantine容错 拜占庭式建筑 人工智能 分布式计算 古代史 容错 历史
作者
Qihao Dong,Shengyuan Yang,Zhiyang Dai,Yansong Gao,Shang Wang,Yuan Cao,Anmin Fu,Willy Susilo
出处
期刊:IEEE Transactions on Information Forensics and Security [Institute of Electrical and Electronics Engineers]
卷期号:19: 9714-9729 被引量:22
标识
DOI:10.1109/tifs.2024.3477912
摘要

Byzantine-robust federated learning (FL) endeavors to empower service providers in acquiring a precise global model, even in the presence of potentially malicious FL clients. While considerable strides have been taken in the development of robust aggregation algorithms for FL in recent years, their efficacy is confined to addressing particular forms of Byzantine attacks, and they exhibit vulnerabilities when confronted with a spectrum of attack vectors. Notably, a prevailing issue lies in the heavy reliance of these algorithms on the examination of local model gradients. It is worth noting that an attacker possesses the ability to manipulate a carefully chosen small gradient of a model within a context where there could be millions of gradients available, thereby facilitating adaptive attacks. Drawing inspiration from the foundational Shapley value methodology in game theory, we introduce an effective FL scheme namedCareFL. This scheme is designed to provide robustness against a spectrum of state-of-the-art Byzantine attacks. Unlike approaches that rely on the examination of gradients,CareFLemploys a universal metric, the loss of the local model—independent of specific gradients, to identify potentially malicious clients. Specifically, in each aggregation round, the FL server trains a reference model using a small auxiliary dataset— the auxiliary dataset can be removed with a slight defense degradation trade-off. It employs the Shapley value to assess the contribution of each client-submitted model in minimizing the global model loss. Subsequently, the server selects client models closer to the reference model in terms of Shapley values for the global model update. To reduce the computational overhead ofCareFLwhen the number of clients is relatively scaled-up, we construct its variant, namelyCareFL+ generally by grouping clients. Extensive experimentation conducted on well-established MNIST and CIFAR-10 datasets, encompassing diverse model architectures, including AlexNet, demonstrates thatCareFLconsistently achieves accuracy levels comparable to those attained under attack-free conditions when faced with five formidable attacks.CareFLand CareFL+ outperform six existing state-of-the-art Byzantine-robust FL aggregation methods, includingFLTrust, across both IID and non-IID data distribution settings.
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
7秒前
13秒前
勤劳的翩跹完成签到,获得积分10
13秒前
文静的丹彤完成签到,获得积分10
14秒前
TingtingGZ发布了新的文献求助10
17秒前
蓝意完成签到,获得积分0
19秒前
李健的应助被TingtingGZ采纳,获得10
24秒前
英姑的应助被TingtingGZ采纳,获得10
24秒前
科研通AI6.2的应助被TingtingGZ采纳,获得10
24秒前
上官若男的应助被TingtingGZ采纳,获得10
25秒前
Hello的应助被TingtingGZ采纳,获得10
25秒前
科研通AI65的应助被TingtingGZ采纳,获得10
25秒前
万能图书馆的应助被TingtingGZ采纳,获得10
25秒前
molihuakai的应助被TingtingGZ采纳,获得10
25秒前
李健的小迷弟的应助被TingtingGZ采纳,获得30
25秒前
GingerF的应助被TingtingGZ采纳,获得200
25秒前
32秒前
快乐的稚晴完成签到,获得积分10
41秒前
紫熊完成签到,获得积分10
47秒前
热情菲鹰完成签到,获得积分10
48秒前
Luoyan完成签到,获得积分10
1分钟前
1分钟前
优雅的傲柏完成签到,获得积分10
1分钟前
1分钟前
我想进步完成签到,获得积分10
1分钟前
坚强含烟完成签到,获得积分10
1分钟前
龙龙发布了新的文献求助10
1分钟前
1分钟前
1分钟前
随心所欲完成签到 ,获得积分10
1分钟前
Ava的应助被龙龙采纳,获得10
1分钟前
怕孤单的雪瑶完成签到,获得积分10
1分钟前
陈荆洲完成签到,获得积分10
1分钟前
1分钟前
从容的绿蝶完成签到,获得积分10
2分钟前
如意夏寒完成签到,获得积分10
2分钟前
2分钟前
2分钟前
老戎完成签到 ,获得积分10
2分钟前
2分钟前
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
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
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 8173194
求助须知:如何正确求助?哪些是违规求助? 9565558
关于积分的说明 21780476
捐赠科研通 7767279
什么是DOI,文献DOI怎么找? 3431542
关于科研通互助平台的介绍 2555697
邀请新用户注册赠送积分活动 2476682