Better Together: Attaining the Triad of Byzantine-robust Federated Learning via Local Update Amplification

No Thumbnail Available
File version
Author(s)
Shen, L
Zhang, Y
Wang, J
Bai, G
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
2022
Size
File type(s)
Location
Austin, USA
License
Abstract

Manipulation of local training data and local updates, i.e., the Byzantine poisoning attack, is the main threat arising from the collaborative nature of the federated learning (FL) paradigm. Many Byzantine-robust aggregation algorithms (AGRs) have been proposed to filter out or moderate suspicious local updates uploaded by Byzantine participants at the central aggregator. However, they largely suffer from model quality degradation due to the over-removal of local updates or/and the inefficiency caused by the expensive analysis of the high-dimensional local updates. In this work, we propose AgrAmplifier that aims to simultaneously attain the triad of robustness, fidelity and efficiency for FL. AgrAmplifier features the amplification of the "morality"of local updates to render their maliciousness and benignness clearly distinguishable. It re-organizes the local updates into patches and extracts the most activated features in the patches. This strategy can effectively enhance the robustness of the aggregator, and it also retains high fidelity as the amplified updates become more resistant to local translations. Furthermore, the significant dimension reduction in the feature space greatly benefits the efficiency of the aggregation. AgrAmplifier is compatible with any existing Byzantine-robust mechanism. In this paper, we integrate it with three mainstream ones, i.e., distance-based, prediction-based, and trust bootstrapping-based mechanisms. Our extensive evaluation against five representative poisoning attacks on five datasets across diverse domains demonstrates the consistent enhancement for all of them, with average gains at, and in terms of robustness, fidelity, and efficiency respectively. We release the source code of AgrAmplifier and our artifacts to facilitate future research in this area: https://github.com/UQ-Trust-Lab/AgrAmplifier.

Journal Title
Conference Title
ACSAC '22: Proceedings of the 38th Annual Computer Security Applications Conference
Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
Item Access Status
Note
Access the data
Related item(s)
Subject
Mobile computing
System and network security
Persistent link to this record
Citation
Shen, L; Zhang, Y; Wang, J; Bai, G, Better Together: Attaining the Triad of Byzantine-robust Federated Learning via Local Update Amplification, ACSAC '22: Proceedings of the 38th Annual Computer Security Applications Conference, 2022, pp. 201-213