Academia
Publications
-
Jančička, L., Soukup, D., Koumar, J., Němec, F., & Čejka, T. MFWDD: Model-based Feature Weight Drift Detection Showcased on TLS and QUIC Traffic - Will be in presented CNSM 2024.
-
Jančička, L., Koumar, J., Soukup, D., & Čejka, T. (2024, May). Analysis of Statistical Distribution Changes of Input Features in Network Traffic Classification Domain. In NOMS 2024-2024 IEEE Network Operations and Management Symposium (pp. 1-4). IEEE. LINK
-
Josef Koumar, Karel Hynek, Jaroslav Pešek, and Tomáš Čejka. “NetTiSA: Extended IP flow with time-series features for universal bandwidth-constrained high-speed network traffic classification” Computer Networks, 2024, 110147. DOI: doi.org/10.1016/j.comnet.2023.110147 LINK
-
Josef Koumar, Karel Hynek, and Tomáš Čejka. “Network Traffic Classification based on Single Flow Time Series Analysis.” 2023 19th International Conference on Network and Service Management (CNSM). IEEE, 2023. LINK
-
Josef Koumar, Richard Plný, and Tomáš Čejka. “Enhancing DeCrypto: Finding Cryptocurrency Miners based on Periodic Behavior” 2023 19th International Conference on Network and Service Management (CNSM). IEEE, 2023. LINK
-
Josef Koumar, and Tomas Čejka. “Unevenly Spaced Time Series from Network Traffic.” 2023 7th Network Traffic Measurement and Analysis Conference (TMA). IEEE, 2023. LINK
-
Jaroslav Pesek, Richard Plny, Josef Koumar, Kamil Jeřábek, and Tomáš Cejka, Augmenting Monitoring Infrastructure For Dynamic Software-Defined Networks, 2023 8th International Conference on Smart and Sustainable Technologies, 2023, LINK
-
Josef Koumar, and Tomáš Čejka. “Network traffic classification based on periodic behavior detection.” 2022 18th International Conference on Network and Service Management (CNSM). IEEE, 2022. LINK
Workshops, posters, etc
-
K. Jerabek, J. Koumar, D. Poliakov, and J. Pesek, Workshop on AI and and traffic classification, NECS – PhD Winter School, 2024, LINK
-
J. Koumar, T. Čejka. “Detection and recognition of periodic communication in network traffic” 2022, LINK
Preprints
-
J. Koumar, K. Hynek, T. Cejka and P. Šiška, “Unsupervised Time Series Dataset from a High-Speed ISP Network for Anomaly Detection in Network Traffic”. - will be added to arxiv in matter of days
-
J. Koumar, K. Hynek, J. Pesek, and T. Cejka, “NetTiSA: Extended IP Flow with Time-series Features for Universal Bandwidth-constrained High-speed Network Traffic Classificatio”. LINK
-
Josef Koumar, Karel Hynek, and Tomáš Čejka. “Network Traffic Classification based on Single Flow Time Series Analysis.” LINK
-
Josef Koumar, and Tomas Čejka. “Unevenly Spaced Time Series from Network Traffic.” LINK
Chairing
-
Poster Co-Chair at 20th International Conference on Network and Service Management (CNSM) 2024 LINK
-
Member of Session Committee of PhD Workshop at 20th International Conference on Network and Service Management (CNSM) 2024 LINK
-
Student Poster Session Co-Chair at The 12th Prague Embedded Systems Workshop (PESW) 2024 LINK
Research projects
-
CYBERTHRETS (OYCESNET20221, Use of artificial intelligence for defence against cyber security attacks)
-
Smart ADS (TH04010073, cooperation with Flowmon Networks supported by Technology Agency (TAČR))
-
Flow based Encrypted Traffic Analysis (VJ02010024, security research challenge IMPAKT 1, Ministry of Interior Czech Republic)
-
Grant Agency of the CTU in Prague, grant No. SGS20/210/OHK3/3T/18 funded by the MEYS of the Czech Republic.
What I am working on right now
-
Anomaly detection dataset from CESNET3 network
-
Anomaly detection in ISP networks using time series analysis
-
Clustering of time series
Memberships
- Researcher at Network Traffic Monitoring Lab (Netmon)
- Academic staff member at Digital Design Department at FIT CTU
- President of IEEE Student Branch for CTU, Czechoslovakia Section
- Senator in the Academic SenateSenator in the Academic Senate at Faculty of Information Technology CTU in Prague
- Vice-chairman of the Commission for Evaluation of Education Quality of the Academic Senate of the Faculty of Information Technologies CTU in Prague