CyberdeceptionAtlas · Question → testES

Library / Paper

Paper

HoneyFL: Using Honeypots to Catch Backdoors in Federated Learning

The authors propose HoneyFL, a run-time defense against diverse backdoor attacks in federated learning that uses honeypot clients and differential prediction to handle adaptive attacks. The work reports comparative experiments against five state-of-the-art defense baselines, with detection and false-positive rates reported by the authors and an impact on main-task aggregation described as negligible.

Honeypot

What we know

The authors propose HoneyFL, a run-time defense against diverse backdoor attacks in federated learning that uses honeypot clients and differential prediction to handle adaptive attacks. The work reports comparative experiments against five state-of-the-art defense baselines, with detection and false-positive rates reported by the authors and an impact on main-task aggregation described as negligible.

Evidence limits

Review limited to the Crossref-deposited abstract; the full text was not consulted and results, software, and effectiveness were not independently validated.

Reviewed: author abstract. Full-text results were not analyzed.

Sources and provenance

  1. HoneyFL: Using Honeypots to Catch Backdoors in Federated Learning
    abstract · 2026-10-11

Reviewed: 2026-10-13. This record may change when new evidence is found.

RIS · BibTeX