Domain-adapted LLMs and SLMs do not consistently outperform general models on STRIDE threat classification for 5G, with decoding strategies and model scale affecting validity but gains remaining insufficient for reliable use.
Large language models for cyber security: A systematic literature review
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Threat Modelling using Domain-Adapted Language Models: Empirical Evaluation and Insights
Domain-adapted LLMs and SLMs do not consistently outperform general models on STRIDE threat classification for 5G, with decoding strategies and model scale affecting validity but gains remaining insufficient for reliable use.