VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database

📅 2026-04-08
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the limitations of existing vulnerability databases, which predominantly rely on relational models that struggle to capture complex inter-vulnerability relationships and lack capabilities for real-time, multi-source integration and user-friendly access. To overcome these challenges, we propose and implement a dynamic, open vulnerability knowledge graph platform that uniquely integrates large language model (LLM) embeddings with graph database technology. The system continuously aggregates authoritative security data sources and enables semantically enriched vulnerability representations. It offers an interactive web-based visualization interface alongside a RESTful API, effectively supporting both expert and non-expert users in efficient risk assessment and threat prioritization. The platform is publicly accessible at http://34.129.186.158/, providing a scalable, real-time, and intuitive analytical infrastructure for cybersecurity research and decision-making.
📝 Abstract
Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public repositories, such as the National Vulnerability Database and CVE details, are regularly updated, but predominantly utilize relational data models that lack native support for representing complex, interconnected structures. To address this, recent research has proposed graph-based vulnerability models. However, these systems often require complex setup procedures, lack real-time multi-source integration, and offer limited accessibility for direct data retrieval and analysis. We present VulGD, a dynamic open-access vulnerability graph database that continuously aggregates cybersecurity data from authoritative repositories. Designed for both expert and non-expert users, VulGD provides a unified web interface and a public API for interactive graph exploration and automated data access. Additionally, VulGD integrates embeddings from large language models (LLMs) to enrich vulnerability description representations, facilitating more accurate vulnerability risk assessment and threat prioritization. VulGD represents a practical and extensible platform for cybersecurity research and decision-making. The live system is publicly accessible at http://34.129.186.158/.
Problem

Research questions and friction points this paper is trying to address.

vulnerability graph database
relational data models
multi-source integration
data accessibility
cybersecurity risk assessment
Innovation

Methods, ideas, or system contributions that make the work stand out.

vulnerability graph database
large language models
dynamic data integration
open-access API
cybersecurity risk assessment
🔎 Similar Papers
No similar papers found.
L
Luat Do
Department of Computer Science and Information Technology, La Trobe University, Melbourne, Australia
J
Jiao Yin
Institute for Sustainable Industries and Liveable Cities, Victoria University, Melbourne, Australia
Jinli Cao
Jinli Cao
La Trobe University
Internet computingXML dataWeb ServiceDatabase systems
Hua Wang
Hua Wang
Professor, Victoria University
E-commerceAccess controlCloud computingBig data