Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper investigates the application of large language models (LLMs) to automatic text simplification (ATS) of Common Vulnerability and Exposure (CVE) descriptions, a task previously unexplored in the cybersecurity domain. The authors created a baseline for cybersecurity ATS and a test dataset of 40 CVE descriptions, which were evaluated by cybersecurity experts. Results indicate that while LLMs can superficially simplify text, they often fail to preserve the original meaning.
LLMs can make cybersecurity vulnerability descriptions *look* simpler, but don't trust them to actually preserve the meaning.
Understanding cyber security is increasingly important for individuals and organizations. However, a lot of information related to cyber security can be difficult to understand to those not familiar with the topic. In this study, we focus on investigating how large language models (LLMs) could be utilized in automatic text simplification (ATS) of Common Vulnerability and Exposure (CVE) descriptions. Automatic text simplification has been studied in several contexts, such as medical, scientific, and news texts, but it has not yet been studied to simplify texts in the rapidly changing and complex domain of cyber security. We created a baseline for cyber security ATS and a test dataset of 40 CVE descriptions, evaluated by two groups of cyber security experts in two survey rounds. We have found that while out-of-the box LLMs can make the text appear simpler, they struggle with meaning preservation. Code and data are available at https://version.aalto.fi/gitlab/vehomav1/simplification\_nmi.