What question did this study set out to answer?

This study aims to explore the use of LLMs in automating cybersecurity threat modeling to improve efficiency and quality.

Automating Cybersecurity Threat Analysis with LLMs

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial investigates LLMs for enhancing threat modeling in cyber-physical systems, suggesting efficiency gains.

This study aims to explore the use of LLMs in automating cybersecurity threat modeling to improve efficiency and quality.
Utilized STRIDE methodology for threat identification and DREAD framework for risk assessment.
Compared performance of single-agent and dual-agent LLM setups.
Evaluated model coherence and reliability across various system domains including web and AI.
LLMs demonstrated promising capabilities in automating threat modeling tasks.
Efficiency improvements were noted, with trade-offs observed between simplicity and precision.
Performance varied depending on interaction model, highlighting potential for further optimization.

Zelenskiy et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark