Local Model Poisoning Attacks to Byzantine-Robust Federated Learning

Authors: 

Minghong Fang, Iowa State University; Xiaoyu Cao, Jinyuan Jia, and Neil Gong, Duke University

Abstract: 

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 (e.g., 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.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {247652,
author = {Minghong Fang and Xiaoyu Cao and Jinyuan Jia and Neil Gong},
title = {Local Model Poisoning Attacks to Byzantine-Robust Federated Learning},
booktitle = {29th {USENIX} Security Symposium ({USENIX} Security 20)},
year = {2020},
isbn = {978-1-939133-17-5},
pages = {1605--1622},
url = {https://www.usenix.org/conference/usenixsecurity20/presentation/fang},
publisher = {{USENIX} Association},
month = aug,
}

Presentation Video