Karel Hynek

Taming Volatility: Stable and Private QUIC Classification with Federated Learning

2025 · arXiv (Cornell University)

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 …

Advanced similarity metrics for IP flow data analytics

2026 · Computer Networks

Machine learning techniques provide powerful tools for analysis of encrypted network traffic. We present a novel set of features and a distance measure suitable for a wide variety of distance-based machine learning techniques useful in …