Deep Model Poisoning Attack on Federated Learning

Federated learning is a novel distributed learning framework, which enables thousands of participants to collaboratively construct a deep learning model. In order to protect confidentiality of the training data, the shared information between server and participants are only limited to model paramet...

Full description

Saved in:
Bibliographic Details
Published in:Future internet Vol. 13; no. 3; p. 73
Main Authors: Zhou, Xingchen, Xu, Ming, Wu, Yiming, Zheng, Ning
Format: Journal Article
Language:English
Published: Basel MDPI AG 01.03.2021
Subjects:
Algorithms
Collaborative learning
Data processing
Datasets
decentralized approach
Deep learning
Federated learning
Internet
Machine learning
Mathematical models
model poisoning attack
Neural networks
Optimization
Parameter modification
Poisoning
Poisons
Privacy
Stealth technology
ISSN:1999-5903, 1999-5903
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Federated learning is a novel distributed learning framework, which enables thousands of participants to collaboratively construct a deep learning model. In order to protect confidentiality of the training data, the shared information between server and participants are only limited to model parameters. However, this setting is vulnerable to model poisoning attack, since the participants have permission to modify the model parameters. In this paper, we perform systematic investigation for such threats in federated learning and propose a novel optimization-based model poisoning attack. Different from existing methods, we primarily focus on the effectiveness, persistence and stealth of attacks. Numerical experiments demonstrate that the proposed method can not only achieve high attack success rate, but it is also stealthy enough to bypass two existing defense methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1999-5903
1999-5903
DOI:10.3390/fi13030073