From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks

arXiv cs.AI / 4/6/2026

💬 OpinionIdeas & Deep AnalysisTools & Practical UsageModels & Research

共有:

Key Points

The paper introduces a new dataset that pairs CAPEC and CWE descriptions with vulnerable code snippets to address limitations of existing vulnerability datasets that lack detailed code-to-vulnerability mappings.
It uses GPT-4o, Llama, and Claude to generate targeted examples whose vulnerabilities align with specific CAPEC/CWE documentation.
Preliminary results indicate the generated code is highly consistent across the three LLMs, with reported 0.98 cosine similarity among the code outputs.
The dataset contains 615 CAPEC code snippets across Java, Python, and JavaScript and is positioned as a resource for research into vulnerability understanding as well as training ML models for vulnerability detection and remediation.

Abstract

The increasing complexity and volume of software systems have heightened the importance of identifying and mitigating security vulnerabilities. The existing software vulnerability datasets frequently fall short in providing comprehensive, detailed code snippets explicitly linked to specific vulnerability descriptions, reducing their utility for advanced research and hindering efforts to develop a deeper understanding of security vulnerabilities. To address this challenge, we present a novel dataset that provides examples of vulnerable code snippets corresponding to Common Attack Pattern Enumerations and Classifications (CAPEC) and Common Weakness Enumeration (CWE) descriptions. By employing the capabilities of Generative Pre-trained Transformer (GPT) models, we have developed a robust methodology for generating these examples. Our approach utilizes GPT-4o, Llama and Claude models to generate code snippets that exhibit specific vulnerabilities as described in CAPEC and CWE documentation. This dataset not only enhances the understanding of security vulnerabilities in code but also serves as a valuable resource for training machine learning models focused on automatic vulnerability detection and remediation. Preliminary evaluations suggest that the dataset generated by Large Language Models demonstrates high accuracy and can serve as a reliable reference for vulnerability identification systems. We found consistent results across the three models, with 0.98 cosine similarity among codes. The final dataset comprises 615 CAPEC code snippets in three programming languages: Java, Python, and JavaScript, making it one of the most extensive and diverse resources in this domain.