Taming Volatility: Stable and Private QUIC Classification with Federated Learning

Result code in 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>

Alternative codes found

RIV/68407700:21240/25:00387084

Result on the web

<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>

Result language

angličtina

Original language name

Taming Volatility: Stable and Private QUIC Classification with Federated Learning

Original language description

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.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

20202 - Communication engineering and systems

Project

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

Continuities

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

Publication year

2025

Confidentiality

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

Article name in the collection

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

ISBN

978-3-903176-75-1

ISSN

2165-963X

e-ISSN

—

Number of pages

5

Pages from-to

—

Publisher name

IEEE

Place of publication

New York, Spojené státy

Event location

Bologna, Italy

Event date

Oct 27, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—