VulGD Dynamic Data Pipeline Workflow

논문 컨텍스트

Paper title: VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database 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/. Passages referencing this figure: tion and transformation, LLM integration, comprehensive source coverage, and a user-friendly web-based interface. This holistic approach aligns with the growing need for cybersecurity solutions that are continuously updated and capable of using advanced AI methods to reveal deeper insights into an ever-evolving threat landscape. 3 Methodology We first give an overview of the design of the system. Fig. 1 presents the architecture of VulGD, which comprises four main components: (1) Compute Server & Graph Database , (2) Dynamic Data Pipeline , (3) LLM Embedder , and (4) Web Interface & API . Figure 1: Overview of the VulGD system architecture. The following subsections describe each component in more detail. First, we briefly introduce Compute Server and Graph Database in Section A, w ontinuously updated and capable of using advanced AI methods to reveal deeper insights into an ever-evolving threat landscape. 3 Methodology We first give an overview of the design of the system. Fig. 1 presents the architecture of VulGD, which comprises four main components: (1) Compute Server & Graph Database , (2) Dynamic Data Pipeline , (3) LLM Embedder , and (4) Web Interface & API . Figure 1: Overview of the VulGD system architecture. The following subsections describe each component in more detail. First, we briefly introduce Compute Server and Graph Database in Section A, which handle data storage and orchestration. Section B presents the Dynamic Data Pipeline for continuous data collection, preprocessing, and migration. Section C discusses the LLM Embedder for on-demand em