← Back to all news
arXiv Machine Learning By Georgia Argyrou, Aymen Bahrouny, Hedi Fendriy, Alexander Jung

Byzantine-Robust Federated Fire Detection with a Rotating Coordinator

Read the original on arXiv Machine Learning →

The paper introduces a federated learning approach for indoor fire detection that tackles three practical challenges: limited uplink bandwidth, Byzantine clients, and reliance on a single fixed aggregation server. It presents a curated dataset from eight public sources, an edge‑deployable detector with up to 10× compression of model updates, and a semi‑decentralized Byzantine‑robust FL method using a rotating coordinator to mitigate stealthy attacks and eliminate single points of failure. Experiments show that the rotating‑coordinator method matches the accuracy and detection speed of a fixed‑server counterpart and is feasible in a physically distributed six‑node cloud deployment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 7

Federated Learning for Object Detection: Enabling Collaborative Drone Learning Without Centralizing Data

arXiv:2607. 02636v1 Announce Type: cross Abstract: Object detection is a fundamental capability for AI-driven perception in safety-critical drone and edge-vision systems, including disaster response, operational security environments, infrastructure monitoring and defense applications.

By Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris, Joaquin del Rio, Oleksii Sliusarenko, Xabi Uribe-Etxebarria
computer-visionroboticssafety
More like this →
arXiv Machine Learning
Sep 15

End-to-End Verifiable and Robust Federated Learning

arXiv:2609.15521v1 Announce Type: new Abstract: Federated learning enables multiple parties to train a shared model without centralizing raw data with the help of an aggregator, but introduces integr...

By Doryan Lesaignoux, Enrique M\'armol Campos, Gabriele Spini, Jos\'e L. Hern\'andez-Ramos, Stephan Krenn
More like this →
arXiv Machine Learning
Sep 4

A Nesterov-Accelerated Byzantine-Robust Federated Learning

The paper proposes Byrd-NAFL, a Byzantine‑robust federated learning algorithm that incorporates Nesterov’s momentum and resilient aggregation rules. It achieves fast and safe convergence under non‑convex, smooth loss functions with relaxed gradient assumptions, and provides a finite‑time convergence guarantee. Experiments show that Byrd-NAFL outperforms existing methods in convergence speed, accuracy, and resilience to various malicious attacks.

By Lihan Xu, Xiaoyi Fan, Gang Wang, Runhao Zeng, Xiping Hu, Yanjie Dong
agentsbenchmarks
More like this →