3 papers
cs.LG2025
When Simple Model Just Works: Is Network Traffic Classification in Crisis?
Kamil Jerabek, Jan Luxemburk, Richard Plny +3
Machine learning has been applied to network traffic classification (TC) for over two decades. While early efforts used shallow models, the latter 2010s saw a shift toward complex…
cs.LG2025
Universal Embedding Function for Traffic Classification via QUIC Domain Recognition Pretraining: A Transfer Learning Success
Jan Luxemburk, Karel Hynek, Richard Plný +1
Encrypted traffic classification (TC) methods must adapt to new protocols and extensions as well as to advancements in other machine learning fields. In this paper, we adopt a tran…
cs.LG2023
DataZoo: Streamlining Traffic Classification Experiments
Jan Luxemburk, Karel Hynek
The machine learning communities, such as those around computer vision or natural language processing, have developed numerous supportive tools and benchmark datasets to accelerate…