Metraipolis › archive › dc_c3735e76da2e
Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs — arXiv:2610.19968
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19968
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:19:12.538Z
- SHA-256 of the archived text
3c6d70ac241543a541b75ec7bc717b68a724cecf2cf3b43b71b3db84f807ac59- Stable URL of this page
https://metraipolis.com/documento/dc_c3735e76da2e
How to cite
Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs — arXiv:2610.19968 — arXiv (en), https://arxiv.org/abs/2610.19968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c3735e76da2e (Metraipolis archive dc_c3735e76da2e, sha256 3c6d70ac241543a541b75ec7bc717b68a724cecf2cf3b43b71b3db84f807ac59)
BibTeX
@misc{dcc3735e76da2e,
title = {Safe-FCL: Continual Risk Awareness and Fine-Grained Safety Aggregation for Federated Continual Learning of LLMs — arXiv:2610.19968},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19968},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c3735e76da2e; sha256 3c6d70ac241543a541b75ec7bc717b68a724cecf2cf3b43b71b3db84f807ac59},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated fine-tuning enables large language models (LLMs) to learn collaboratively from distributed client data, but malicious client updates can compromise global model safety. As federated tasks evolve, changing malicious update patterns challenge the ability of existing defenses to maintain reliable risk detection over time. To address this challenge, we propose Safe-FCL, a framework integrating continual risk awareness with fine-grained safety aggregation for federated continual learning of LLMs. Specifically, the Continual Risk Awareness (CRA) mechanism learns emerging risk patterns across sequential tasks and constrains detector updates using a protective subspace derived from historical features, mitigating forgetting of previously learned malicious patterns while adapting to new risks. To translate risk awareness into aggregation-level safety control, the Fine-Grained Safety Aggregation (FGSA) mechanism combines client-level risk assessments from CRA with module-level deviations from historical update behavior to adaptively regulate aggregation contributions, suppressing potentially malicious updates while minimizing unnecessary restrictions on benign updates. Extensive experiments demonstrate that Safe-FCL outperforms current SOTA methods, improving global-model Rule and MD-Judge scores in federated continual learning by 0.41% and 0.64%, respectively, while increasing average risk recognition accuracy by 2.01%. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.19968 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T13:53:35.680Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).