#AppSec
#Whitepaper
#Threat_Research
"Comparative Analysis of Large Language Model Performance in Automated Threat Modeling: A WordPress Application Case Study", Aug. 2025.
]-> Repo

// This study investigates the use of LLMs as an assistant to conduct threat models of systems or apps. It researches the efficacy of a sample of modern LLMs against a constant system, a WordPress application deployed in Kubernetes. It compares the results based on four key metrics: threat coverage, completeness & depth of explanation, consistency, and false positive rate