Puertas i Prats, EloiCamps i Regàs, Hug2025-09-152025-09-152025-06-30https://hdl.handle.net/2445/223152Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona. Any: 2025. Tutor: Eloi Puertas i PratsProactive cybersecurity measures are essential for effective risk mitigation in increasingly complex and evolving digital environments. Achieving this requires not only the collection of relevant data but also its accurate interpretation and the development of specialized analytical frameworks. This project focuses on addressing the challenge of interpreting cyber threat data by classifying honeypot data, provided by the Global Cyber Alliance (GCA), according to the MITRE ATT&CK Matrix—a widely recognized framework for understanding adversarial behavior. In an era dominated by large language models (LLMs), we investigate an alternative approach based on smaller, specialized models. Specifically, we design a custom architecture of lightweight models and train them for the task, evaluating their performance across various configurations. Our findings demonstrate that these models can, in certain scenarios, outperform larger LLMs in both accuracy and efficiency, offering a more sustainable and cost-effective solution for targeted cybersecurity applications.35 p.application/pdfengcc-by-nc-nd (c) Hug Camps i Regàs, 2025http://creativecommons.org/licenses/by-nc-nd/3.0/es/Tractament del llenguatge natural (Informàtica)Natural language processing (Computer science)Seguretat de les xarxes d'ordinadorsTreballs de fi de màsterNatural language processing (Computer science)Computer securityComputer network securityMaster's thesisinfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccess