Josef Koumar

According to our database, Josef Koumar authored at least 12 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of six.
• Erdős number of five.

2025

When Simple Model Just Works: Is Network Traffic Classification in Crisis?

Kamil Jerábek, Jan Luxemburk, Richard Plný, Josef Koumar, Jaroslav Pesek, Karel Hynek

CoRR, June, 2025

Comparative Analysis of Deep Learning Models for Real-World ISP Network Traffic Forecasting.

Josef Koumar, Timotej Smolen, Kamil Jerábek, Tomás Cejka

CoRR, March, 2025

Towards Building Network Outlier Detection System for Network Traffic Monitoring.

Josef Koumar, Jaroslav Pesek, Kamil Jerábek, Tomás Cejka

Proceedings of the NOMS 2025 IEEE Network Operations and Management Symposium, 2025

Explainable Anomaly Detection in Network Traffic Using LLM.

Kamil Jerábek, Josef Koumar, Jirí Setinský, Jaroslav Pesek

Proceedings of the NOMS 2025 IEEE Network Operations and Management Symposium, 2025

2024

CESNET-TimeSeries24: Time Series Dataset for Network Traffic Anomaly Detection and Forecasting.

Josef Koumar, Karel Hynek, Tomás Cejka, Pavel Siska

CoRR, 2024

NetTiSA: Extended IP flow with time-series features for universal bandwidth-constrained high-speed network traffic classification.

Josef Koumar, Karel Hynek, Jaroslav Pesek, Tomás Cejka

Comput. Networks, 2024

Analysis of Statistical Distribution Changes of Input Features in Network Traffic Classification Domain.

Lukás Jancicka, Josef Koumar, Dominik Soukup, Tomás Cejka

Proceedings of the NOMS 2024 IEEE Network Operations and Management Symposium, 2024

MFWDD: Model-based Feature Weight Drift Detection Showcased on TLS and QUIC Traffic.

Lukás Jancicka, Dominik Soukup, Josef Koumar, Filip Nemec, Tomás Cejka

Proceedings of the 20th International Conference on Network and Service Management, 2024

2023

Unevenly Spaced Time Series from Network Traffic.

Josef Koumar, Tomás Cejka

Proceedings of the 7th Network Traffic Measurement and Analysis Conference, 2023

Enhancing DeCrypto: Finding Cryptocurrency Miners Based on Periodic Behavior.

Josef Koumar, Richard Plný, Tomás Cejka

Proceedings of the 19th International Conference on Network and Service Management, 2023

Network Traffic Classification Based on Single Flow Time Series Analysis.

Josef Koumar, Karel Hynek, Tomás Cejka

Proceedings of the 19th International Conference on Network and Service Management, 2023

2022

Network traffic classification based on periodic behavior detection.

Josef Koumar, Tomás Cejka

Proceedings of the 18th International Conference on Network and Service Management, 2022