Institutional Repository of Vilnius University
Sintetinių duomenų generavimas kibernetinio saugumo pratyboms /
Abstract
dc:descriptionSynthetic data provides a safe and controlled environment for training cybersecurity professionals, allowing them to learn and test systems without the risk of violating the privacy of real individuals or confidential information. In this work, a prototype of a synthetic data generation tool was created, which allows generating structured, realistic data from a database according to predefined scenarios. The work analyzes synthetic data generation methods, reviewing existing solutions, their advantages and disadvantages. It also examines popular data generation methods, including GAN (Generative Adversarial Networks) and GPT models, and their application in cybersecurity exercises. In addition, the need for synthetic data generation and its application in digital forensics are reviewed. The main result of the work is the creation of a prototype of a synthetic data generation tool, which allows generating different types of data from a database according to specified scenarios. The system uses a PostgreSQL database for storing initial data and SQLite databases for exporting results. The prototype of the tool features a modular architecture that ensures easy extensibility and maintenance. The functionality of the prototype includes data generation based on scripts, timestamp management, noise generation, and parameter-based search capabilities. The system is configured using YAML configuration files, and the user interface is implemented via the command line, which allows for easy integration of the tool into larger systems and automation of processes. This work not only presents a practical solution for synthetic data generation, but also lays the foundation for further development of the system by including additional data types, expanding scripting capabilities, and improving data generation algorithms.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kuznecovas, Aleksandras,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD229555402&prefLang=en_US