What type of study is this?

This is a Literature Review study.

September 18, 2025

Investigating the use of Large Language Models in software security requirements: Results of a literature review

Key Points

The review identifies key applications of large language models in security requirements tasks, emphasizing their diverse capabilities.
Evaluation metrics for assessing large language models' performance in supporting secure software engineering tasks were reviewed.
Various families of large language models, such as GPT and BERT, were characterized along with their architectures and techniques.
Current research reveals significant gaps and opportunities for leveraging large language models in enhancing software security.

Abstract

This study investigates the application of Large Language Models (LLMs) in the context of security requirements engineering through the conduction of a rapid literature review. The review enabled the characterization of current research in this domain with respect to: (i) the purposes for which LLMs are employed in security requirements activities; (ii) the families of LLMs explored (e.g., GPT, BERT, LLaMA), their capabilities (e.g., classification, generation), and underlying architectures (e.g., encoder, decoder, encoder-decoder); (iii) the techniques adopted for conditioning or guiding LLM behavior; (iv) the datasets used to train, fine-tune, or validate these models; and (v) the evaluation metrics applied to assess the performance of LLMs in supporting security requirements tasks. The findings contribute to a structured understanding of the current state of research and highlight key trends, gaps, and opportunities for advancing the use of LLMs in secure software engineering.

Mark Helpful

Bookmark

Relay