Fed-Frenemy: robust screening of compromised clients, balancing heterogeneity

Xiaoxiao Li; Dian Wang

doi:10.1117/12.3030655

5 June 2024 Fed-Frenemy: robust screening of compromised clients, balancing heterogeneity

Xiaoxiao Li, Dian Wang

Proceedings Volume 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024); 131635M (2024) https://doi.org/10.1117/12.3030655
Event: International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 2024, Xi'an, China

Abstract

Federated learning has emerged as a new paradigm of distributed learning that trains models jointly without exchanging data. However, it still faces the risk of heterogeneous data distribution and backdoor attacks. Generally speaking, due to the data heterogeneity, the local convergence to the local optimum usually deviates from the global optimum, resulting in the drift of federated learning and hindering the efficiency of model aggregation. Moreover, due to the possibility of different degrees of backdoor attacks, the addition of malicious clients interferes with the global aggregation or even does not converge. We propose FedFre an automatic weight adjustment method to aggregate globally submitted models. This new meta-learning algorithm used on federated learning assigns weights to each client based on its gradient direction. To assign this weight, we perform a meta-gradient descent step on the clean, unbiased few-shot dataset owned by the server to minimize this loss. Applying this technique, we get impressive results both for client aggregation of heterogeneous data distributions and for client aggregation under a large proportion of attacks.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Xiaoxiao Li and Dian Wang "Fed-Frenemy: robust screening of compromised clients, balancing heterogeneity", Proc. SPIE 13163, Fourth International Conference on Mechanical, Electronics, and Electrical and Automation Control (METMS 2024), 131635M (5 June 2024); https://doi.org/10.1117/12.3030655

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Machine learning

Education and training

Data modeling

Lithium

Adversarial training

Computer security

Data privacy

Show All Keywords

Keywords/Phrases

Search In:

Publication Years