The goal of this project is to provide neural network architectures for traffic classification and their pre-trained weights.
The newest network architecture is named Multi-modal CESNET v2 (mm-CESNET-v2) and is visualized in the following picture. See the getting started page and models reference for more information.
๐ธ ๐ธ See a related project CESNET DataZoo providing large TLS and QUIC traffic datasets. ๐ธ ๐ธ
๐ ๐ Example Jupyter notebooks are included in a separate CESNET Traffic Classification Examples repo. ๐ ๐
Install the package from pip with:
pip install cesnet-models
or for editable install with:
pip install -e git+https://github.com/CESNET/cesnet-models
Models from the following papers are included:
-
Fine-grained TLS services classification with reject option
Jan Luxemburk and Tomรกลก ฤejka
Computer Networks, 2023 -
Encrypted traffic classification: the QUIC case
Jan Luxemburk and Karel Hynek
2023 7th Network Traffic Measurement and Analysis Conference (TMA)