What question did this study set out to answer?

To develop a method that ensures the security of global models in federated learning systems through data verification.

February 26, 2026

Trust-Model-Based Method for Protecting Global Models in Federated Learning Systems

Key Points

To develop a method that ensures the security of global models in federated learning systems through data verification.
Proposed method utilizes a trusted group of nodes for data verification.
Focused on ensuring only correct updates are included in global model aggregation.
Experimental validation of method effectiveness against adversarial threats.
Successfully identifies and isolates adversaries conducting label-flipping attacks.
Effectively mitigates noise-injection threats during model aggregation process.

Abstract

The problem of ensuring the security of a global computational model in federated learning systems is considered. A method is proposed that is based on data verification using a trusted group of nodes and ensures that only correct updates are taken into account during the global model aggregation process. It is experimentally demonstrated that the developed method ensures accurate identification and isolation of adversaries implementing label-flipping and noise-injection threats.

KI fragen

Bookmark

Cite This Study

Krundyshev et al. (Mon,) studied this question.

synapsesocial.com/papers/699fe2fe95ddcd3a253e6898 https://doi.org/https://doi.org/10.3103/s0146411625700762

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

KI fragen

Bookmark