Leveraging Tabular Transformer Architectures for Operating System Fingerprinting

arXiv Preprint

Authors: Rubén Pérez-Jove, Alejandro Pazos, Jose Vázquez-Naya

Description

This project focuses on Operating System fingerprinting using Tabular Transformers with different datasets. The aim is to explore the application of advanced deep learning architectures in the field of network security. The repositoy is structured in different folders, according to the experiments executed on the three different datasets used.

Installation

The project was developed using Python 3.10.8. To install the necessary dependencies, run the following command.

pip install -r requirements.txt

Datasets

The datasets used in this project are not uploaded to this repository due to GitHub file size restrictions. They can be downloaded from the original sources, listed below:

• DAT1: lastovicka_2023_passiveOSRevisited
• DAT2: lastovicka_2019_usingTLS
• DAT3: nmap-7.94_2023_OSdb

Results

The results of the experiments are documented in the Results Section. This includes performance metrics, visualizations, and analysis.

Contributing

Contributions are welcome! Please contact the main author or submit a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for details.

Acknowledgements

Special thanks to my supervisors, Alejandro Pazos and Jose Vázquez-Naya, and the RNASA-IMEDIR research group for their support.