VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database
- URL: http://arxiv.org/abs/2604.06967v1
- Date: Wed, 08 Apr 2026 11:32:58 GMT
- Title: VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database
- Abstract summary: VulGD is a dynamic open-access vulnerability graph database that continuously aggregates cybersecurity data from authoritative repositories.<n>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.
- Score: 3.864032833772679
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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/.
Related papers
- Construction and Natural Language Querying of a Cybersecurity Knowledge Graph [0.0]
This paper proposes an approach that combines the construction of a cybersecurity knowledge graph with natural language-based interrogation.<n>The proposed methodology relies on data collected from the National Vulnerability Database (NVD) through its REST API.<n>The knowledge graph is deployed on Neo4j Aura Cloud and queried through an AI-assisted interface that translates natural language queries into Cypher language.
arXiv Detail & Related papers (2026-09-07T15:20:35Z) - CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild [49.44069582581181]
CyberFactory transforms public vulnerability artifacts, including CVEs from the wild, into executable and verifiable task instances.<n>It uses a reusable vulnerability-analysis skill to guide the teacher through source inspection, problem solving with domain prior, and evidence-based validation.<n>On CyberGym, modelname reaches 52.4% Pass@1 under a one-hour budget, improving over its Qwen3.5 base model by +22.8 points.
arXiv Detail & Related papers (2026-08-24T12:30:10Z) - GCVE: A Decentralized Model for Vulnerability Identification, Publication, and Operational Enrichment [51.77969450792284]
The Global CVE initiative (G) proposes a decentralized, open, and identifier model for vulnerability identification, publication, and enrichment.<n>This paper presents G as socio-technical effort combining autonomous G Numbering Authorities, lightweight allocation rules, distributed publication, open Best Current Practices, and practical reference implementations.
arXiv Detail & Related papers (2026-05-30T19:03:39Z) - Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
arXiv Detail & Related papers (2026-01-29T03:53:25Z) - VulRG: Multi-Level Explainable Vulnerability Patch Ranking for Complex Systems Using Graphs [20.407534993667607]
This work introduces a graph-based framework for vulnerability patch prioritization.<n>It integrates diverse data sources and metrics into a universally applicable model.<n> refined risk metrics enable detailed assessments at the component, asset, and system levels.
arXiv Detail & Related papers (2025-02-16T14:21:52Z) - Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
Anonymizing text that contains sensitive information is crucial for a wide range of applications.<n>Existing techniques face the emerging challenges of the re-identification ability of large language models.<n>We propose a framework composed of three key components: a privacy evaluator, a utility evaluator, and an optimization component.
arXiv Detail & Related papers (2024-07-16T14:28:56Z) - "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs)
In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
arXiv Detail & Related papers (2024-06-26T05:36:23Z) - VulZoo: A Comprehensive Vulnerability Intelligence Dataset [12.229092589037808]
VulZoo is a comprehensive vulnerability intelligence dataset that covers 17 popular vulnerability information sources.
We make VulZoo publicly available and maintain it with incremental updates to facilitate future research.
arXiv Detail & Related papers (2024-06-24T06:39:07Z) - Profile of Vulnerability Remediations in Dependencies Using Graph
Analysis [40.35284812745255]
This research introduces graph analysis methods and a modified Graph Attention Convolutional Neural Network (GAT) model.
We analyze control flow graphs to profile breaking changes in applications occurring from dependency upgrades intended to remediate vulnerabilities.
Results demonstrate the effectiveness of the enhanced GAT model in offering nuanced insights into the relational dynamics of code vulnerabilities.
arXiv Detail & Related papers (2024-03-08T02:01:47Z) - Using Program Knowledge Graph to Uncover Software Vulnerabilities [0.0]
A knowledge graph constructed with information extracted from the system along with the desired security behavior can be utilized to identify complex security vulnerabilities hidden underneath the systems.
We present a novel approach of using Program Knowledge Graph that is embedded with fine-grained execution information of the systems.
arXiv Detail & Related papers (2023-12-08T03:38:43Z) - VELVET: a noVel Ensemble Learning approach to automatically locate
VulnErable sTatements [62.93814803258067]
This paper presents VELVET, a novel ensemble learning approach to locate vulnerable statements in source code.
Our model combines graph-based and sequence-based neural networks to successfully capture the local and global context of a program graph.
VELVET achieves 99.6% and 43.6% top-1 accuracy over synthetic data and real-world data, respectively.
arXiv Detail & Related papers (2021-12-20T22:45:27Z) - An Automated, End-to-End Framework for Modeling Attacks From
Vulnerability Descriptions [46.40410084504383]
In order to derive a relevant attack graph, up-to-date information on known attack techniques should be represented as interaction rules.
We present a novel, end-to-end, automated framework for modeling new attack techniques from textual description of a security vulnerability.
arXiv Detail & Related papers (2020-08-10T19:27:34Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.