Data Poisoning Attacks on Federated Machine Learning

计算机科学 机器学习 人工智能 协议(科学) 医学 病理 替代医学
作者
Gan Sun,Yang Cong,Jiahua Dong,Qiang Wang,Lingjuan Lyu,Ji Liu
出处
期刊:IEEE Internet of Things Journal [Institute of Electrical and Electronics Engineers]
卷期号:9 (13): 11365-11375 被引量:280
标识
DOI:10.1109/jiot.2021.3128646
摘要

Federated machine learning which enables resource-constrained node devices (e.g., Internet of Things (IoT) devices and smartphones) to establish a knowledge-shared model while keeping the raw data local, could provide privacy preservation, and economic benefit by designing an effective communication protocol. However, this communication protocol can be adopted by attackers to launch data poisoning attacks for different nodes, which has been shown as a big threat to most machine learning models. Therefore, we in this article intend to study the model vulnerability of federated machine learning, and even on IoT systems. To be specific, we here attempt to attacking a popular federated multitask learning framework, which uses a general multitask learning framework to handle statistical challenges in the federated learning setting. The problem of calculating optimal poisoning attacks on federated multitask learning is formulated as a bilevel program, which is adaptive to the arbitrary selection of target nodes and source attacking nodes. We then propose a novel systems-aware optimization method, called as attack on federated learning (AT 2 FL), to efficiently derive the implicit gradients for poisoned data, and further attain optimal attack strategies in the federated machine learning. This is an earlier work, to our knowledge, that explores attacking federated machine learning via data poisoning. Finally, experiments on several real-world data sets demonstrate that when the attackers directly poison the target nodes or indirectly poison the related nodes via using the communication protocol, the federated multitask learning model is sensitive to both poisoning attacks.
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
传奇3的应助被长青采纳,获得10
刚刚
刚刚
柏林完成签到,获得积分10
刚刚
bkagyin的应助被planb采纳,获得10
1秒前
要文献啊完成签到 ,获得积分10
1秒前
嘿哈哈哈哈完成签到,获得积分20
1秒前
11111完成签到,获得积分10
1秒前
1秒前
Munchr1发布了新的文献求助10
1秒前
orixero的应助被芋泥啵啵采纳,获得10
1秒前
2秒前
man完成签到,获得积分20
3秒前
amia完成签到,获得积分10
3秒前
4秒前
4秒前
xx发布了新的文献求助10
4秒前
cherish发布了新的文献求助10
4秒前
皮卡丘发布了新的文献求助10
5秒前
5秒前
zxk发布了新的文献求助10
5秒前
5秒前
6秒前
容与完成签到 ,获得积分10
6秒前
余香的应助被amia采纳,获得10
7秒前
xiongjie发布了新的文献求助10
8秒前
man发布了新的文献求助30
8秒前
yang发布了新的文献求助10
8秒前
酷波er的应助被Lu采纳,获得10
8秒前
Munchr1完成签到,获得积分10
8秒前
10秒前
369ninja发布了新的文献求助10
10秒前
8895发布了新的文献求助10
12秒前
13秒前
14秒前
JamesPei的应助被dianhuaxue采纳,获得10
14秒前
14秒前
小馋猫完成签到,获得积分10
15秒前
yang发布了新的文献求助10
16秒前
liu1223456完成签到,获得积分10
16秒前
ihuu完成签到,获得积分10
16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
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
八旗制度の研究 600
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
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 8184267
求助须知:如何正确求助?哪些是违规求助? 9573323
关于积分的说明 21830790
捐赠科研通 7781314
什么是DOI,文献DOI怎么找? 3434307
关于科研通互助平台的介绍 2558389
邀请新用户注册赠送积分活动 2480817