LATIDIA · Ciberseguridad

Federated Learning in the Wild: A Comparative Study for Cybersecurity under Non-IID and Unbalanced Settings (Aprendizaje federado en la naturaleza: un estudio comparativo para la ciberseguridad en entornos

arXiv: 2509.17836v2Tipo de anuncio: reemplazar Resumen: Las técnicas de aprendizaje automático (ML) han demostrado un gran potencial para el análisis del tráfico de red; sin embargo, su efectividad depende del acceso a información representativa y actualizada

La noticia

arXiv:2509.17836v2 Announce Type: replace Abstract: Machine Learning (ML) techniques have shown strong potential for network traffic analysis; however, their effectiveness depends on access to representative, up-to-date datasets, which is limited in cybersecurity due to privacy and data-sharing restrictions. To address this challenge, Federated Learning (FL) has recently emerged as a novel paradigm that enables collaborative training of ML models across multiple clients while ensuring that sensitive data remains local. Nevertheless, Federated Averaging (FedAvg), the canonical FL algorithm, has shown poor convergence in heterogeneous environments characterised by non-independent and identically distributed (i.i.d.) data distributions and unbalanced dataset sizes across clients, conditions frequently observed in cybersecurity contexts. To overcome these challenges, several