Robust federated learning client selection with combinatorial class representations and data augmentation

Publication Type

Journal Article

Publication Date

5-2025

Abstract

The federated learning (FL) client selection scheme can effectively mitigate global model performance degradation caused by the random aggregation of clients with heterogeneous data. Simultaneously, research has exposed FL’s susceptibility to backdoor attacks. However herein lies the dilemma, traditional client selection methods and backdoor defenses stand at odds, so their integration is an elusive goal. To resolve this, we introduce Grace, a resilient client selection framework blending combinational class sampling with data augmentation. On the client side, Grace first proposes a local model purification method, fortifying the model’s defenses by bolstering its innate robustness. After, local class representations are extracted for server-side client selection. This approach not only shields benign models from backdoor tampering but also allows the server to glean insights into local class representations without infringing upon the client’s privacy. On the server side, Grace introduces a novel representation combination sampling method. Clients are selected based on the interplay of their class representations, a strategy that simultaneously weeds out malicious actors and draws in clients whose data holds unique value. Our extensive experiments highlight Grace’s capabilities. The results are compelling: Grace enhances defense performance by over 50% compared to state-of-the-art (SOTA) backdoor defenses, and, in the best case, improves accuracy by 3.19% compared to SOTA client selection schemes. Consequently, Grace achieves substantial advancements in both security and accuracy.

Keywords

Federated learning, client selection, backdoor defense, data augmentation, representation learning

Discipline

Information Security

Research Areas

Information Systems and Management

Publication

IEEE Transactions on Information Forensics and Security

Volume

20

Issue

1

First Page

6086

Last Page

6100

ISSN

1556-6013

Identifier

10.1109/TIFS.2025.3579290

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TIFS.2025.3579290

This document is currently not available here.

Share

COinS