Bc. Alexander Jandl

Bachelor's thesis

Exploring LLM's for inferring relations between cybersecurity constructs

Exploring LLM's for inferring relations between cybersecurity constructs
Abstract:
Táto práca skúma schopnosť veľkých jazykových modelov, konkrétne GPT-4, odvodiť vzťahy medzi konštruktmi kybernetickej bezpečnosti, ako sú popisy CVE a techniky ATT&CK. Výskum zahŕňa vývoj a testovanie metodológií na mapovanie CVE na techniky ATT&CK a opačne pomocou kľúčových slov generovaných modelom GPT-4. Na hodnotenie účinnosti týchto mapovaní boli použité metriky, ako sú presnosť a pokrytie …more
Abstract:
This work investigates the ability of large language models, specifically GPT-4, to infer relationships between cybersecurity constructs such as descriptions of CVE and ATT&CK techniques. Research includes developing and testing methodologies for mapping CVEs to ATT&CK techniques and vice versa using keywords generated by the GPT-4 model. Metrics such as accuracy and coverage were used to evaluate …more
 

Keywords

LLMs cybersecurity GPT CVE ATT& CK NLP vulnerability impact keywords relation inferrence
 
Language used: English
Date on which the thesis was submitted / produced: 23. 5. 2024
Identifier: https://is.muni.cz/th/su1wp/

Thesis defence

  • Date of defence: 26. 6. 2024
  • Supervisor: Mgr. Ádám Ruman
  • Reader: RNDr. Martin Drašar, Ph.D.

Citation record

Cite this text

Full text of thesis

Contents of on-line thesis archive
Published in Theses:
  • světu
Other ways of accessing the text
Institution archiving the thesis and making it accessible: Masarykova univerzita, Fakulta informatiky
Složka Reference to the local database directory of the institution

Masaryk University

Faculty of Informatics

Bachelor programme / field:
Cybersecurity / Cybersecurity

Theses on a related topic

List of theses with an identical keyword.