Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master device maintains a global model via aggregating the local models from the client devices. The machine learning community recently proposed several federated learning methods that were claimed to be robust against Byzantine failures (eg, system failures, adversarial manipulations) of certain client devices. In this work, we perform the first systematic study on local model poisoning attacks to federated learning. We assume an attacker has compromised some client devices, and the attacker manipulates the local model parameters on the compromised client devices during the learning process such that the global model has a large testing error rate. We formulate our attacks as optimization problems and apply our attacks to four recent Byzantine-robust federated learning methods. Our empirical results on four real-world datasets show that our attacks can substantially increase the error rates of the models learnt by the federated learning methods that were claimed to be robust against Byzantine failures of some client devices. We generalize two defenses for data poisoning attacks to defend against our local model poisoning attacks. Our evaluation results show that one defense can effectively defend against our attacks in some cases, but the defenses are not effective enough in other cases, highlighting the need for new defenses against our local model poisoning attacks to federated learning.
最新文章
- flexbox学习
- ORM系列之三：Dapper
- Python 的安装与配置（Windows）
- Python开发入门与实战3-Django动态页面
- 选择时区的命令tzselect
- phpcmsv9如何实现添加栏目时不在首页内容区显示只在导航栏显示
- The IAR Archive Tool—iarchive
- [BZOJ 1042] [HAOI2008] 硬币购物 【DP + 容斥】
- sublime在Mac osx下安装z-codeing(即emmet)
- showModalDialog-父窗体子窗体
- cout输出各种进制
- 使用python操作RabbitMQ,Redis,Memcache,SQLAlchemy 其二
- 使用 JQueryMobile 点击超链接提示“error loading page” 错误
- Android环境搭建与HelloWorld
- Linux在线安装git(亲测成功)
- error and solve
- 用Python建立连接直接读取与更改Rockwell Control Logix Controller的tag值
- MT【284】构造函数的导数的两类题型
- 一次关于()=>({})的使用
- 关于min_25筛的一些理解