20.500.12556/DKUM-96117 Towards a sustainable cybersecurity governance threat modelling with large language models With the increased complexity of applications and systems, threat modelling struggles to keep pace with the evolution of risks. This article addresses this challenge by exploring how large language models (LLMs) can be leveraged to create comprehensive threat models across different risk assessment methodologies. We examine whether a single generic prompt can support frameworks such as LINDDUN, PASTA, and STRIDE, despite their different requirements. Through this comparative analysis, we identify components that enable AI-based assessments, while acknowledging that privacy, regulatory, and dynamic risks require adaptation of the frameworks. Our findings show that a universal guideline is feasible for broad applications, but adaptation is necessary for effective use. Overall, LLM-based threat modelling improves the accessibility, repeatability, and effectiveness of risk analysis and supports stronger and more sustainable practices. cybersecurity large language models threat modelling sustainability resilient infrastructure SDG 9 kibernetska varnost veliki jezikovni modeli modeliranje groženjcyber trajnost prožna infrastruktura true false true MDPI Angleški jezik Slovenski jezik https://www.mdpi.com/journal/sustainability © 2025 by the authors Članek v reviji 2025-12-02 14:12:11 2025-12-02 14:12:12 2025-12-03 03:11:58 0000-00-00 00:00:00 2025 0 0 15 str. iss. 23, [article no.] 10569 Vol. 17 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 2025-10-03 2025-11-20 2025-11-25 004.7 258988035 10.3390/su172310569 2071-1050 sustainability-17-10569-v2.pdf sustainability-17-10569-v2.pdf 1 2FEA3FB1BDD182AD7455469E74824220 784340a8bda13adbf6548e022d431978353daa7d8f0220539ee04f8149cb149e bcbd85b2-cf80-11f0-9f24-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=201064 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0