3 papers
cs.NI2025
On the Feasibility of Inter-Flow Service Degradation Detection
Balint Bicski, Adrian Pekar
Hardware acceleration in modern networks creates monitoring blind spots by offloading flows to a non-observable state, hindering real-time service degradation (SD) detection. To ad…
cs.NI2025
Taming Volatility: Stable and Private QUIC Classification with Federated Learning
Richard Jozsa, Karel Hynek, Adrian Pekar
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…
cs.NI2024
Early Detection of Network Service Degradation: An Intra-Flow Approach
Balint Bicski, Adrian Pekar
This research presents a novel method for predicting service degradation (SD) in computer networks by leveraging early flow features. Our approach focuses on the observable (O) seg…