Taming Volatility: Stable and Private QUIC Classification with Federated Learning

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F63839172%3A_____%2F25%3A10133832" target="_blank" >RIV/63839172:_____/25:10133832 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21240/25:00387084

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/11297478" target="_blank" >https://ieeexplore.ieee.org/document/11297478</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.23919/CNSM67658.2025.11297478" target="_blank" >10.23919/CNSM67658.2025.11297478</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Taming Volatility: Stable and Private QUIC Classification with Federated Learning

Popis výsledku v původním jazyce

Federated Learning (FL) is a promising approach for privacy-preserving network traffic analysis, but its practical deployment is challenged by the non-IID nature of real-world data. While prior work has addressed statistical heterogeneity, the impact of temporal traffic volatility-the natural daily ebb and flow of network activity-on model stability remains largely unexplored. This volatility can lead to inconsistent data availability at clients, destabilizing the entire training process. In this paper, we systematically address the problem of temporal volatility in federated QUIC classification. We first demonstrate the instability of standard FL in this dynamic setting. We then propose and evaluate a client-side data buffer as a practical mechanism to ensure stable and consistent local training, decoupling it from real-time traffic fluctuations. Using the real-world CESNETQUIC22 dataset partitioned into 14 autonomous clients, we then demonstrate that this approach enables robust convergence. Our results show that a stable federated system achieves a 95.2% F1 score, a mere 2.3 percentage points below a non-private centralized model. This work establishes a blueprint for building operationally stable FL systems for network management, proving that the challenges of dynamic network environments can be overcome with targeted architectural choices.

Název v anglickém jazyce

Taming Volatility: Stable and Private QUIC Classification with Federated Learning

Popis výsledku anglicky

Federated Learning (FL) is a promising approach for privacy-preserving network traffic analysis, but its practical deployment is challenged by the non-IID nature of real-world data. While prior work has addressed statistical heterogeneity, the impact of temporal traffic volatility-the natural daily ebb and flow of network activity-on model stability remains largely unexplored. This volatility can lead to inconsistent data availability at clients, destabilizing the entire training process. In this paper, we systematically address the problem of temporal volatility in federated QUIC classification. We first demonstrate the instability of standard FL in this dynamic setting. We then propose and evaluate a client-side data buffer as a practical mechanism to ensure stable and consistent local training, decoupling it from real-time traffic fluctuations. Using the real-world CESNETQUIC22 dataset partitioned into 14 autonomous clients, we then demonstrate that this approach enables robust convergence. Our results show that a stable federated system achieves a 95.2% F1 score, a mere 2.3 percentage points below a non-private centralized model. This work establishes a blueprint for building operationally stable FL systems for network management, proving that the challenges of dynamic network environments can be overcome with targeted architectural choices.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

<a href="/cs/project/LM2023054" target="_blank" >LM2023054: e-Infrastruktura CZ</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 2025 21st International Conference on Network and Service Management (CNSM)

ISBN

978-3-903176-75-1

ISSN

2165-963X

e-ISSN

—

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

IEEE

Místo vydání

New York, Spojené státy

Místo konání akce

Bologna, Italy

Datum konání akce

27. 10. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—