mlsanityData to 7 Oct 2026

VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection

arXiv 2602.10787 ↗First posted 11 Feb 2026cs.SE cs.AI cs.CRcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Software vulnerability detection (SVD) is a critical challenge in modern systems. Large language models (LLMs) offer natural-language explanations alongside predictions, but most work focuses on binary evaluation, and explanations often lack semantic consistency with Common Weakness Enumeration (CWE) categories. We propose VulReaD, a knowledge-graph-guided approach for vulnerability reasoning and detection that moves beyond binary classification toward CWE-level reasoning. VulReaD leverages a security knowledge graph (KG) as a semantic backbone and uses a strong teacher LLM to generate CWE-consistent contrastive reasoning supervision, enabling student model training without manual annotations. Students are fine-tuned with Odds Ratio Preference Optimization (ORPO) to encourage taxonomy-aligned reasoning while suppressing unsupported explanations. Across three real-world datasets, VulReaD improves binary F1 by 8-10% and multi-class classification by 30% Macro-F1 and 18% Micro-F1 compared to state-of-the-art baselines. Results show that LLMs outperform deep learning baselines in binary detection and that KG-guided reasoning enhances CWE coverage and interpretability.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 23 of its 73 references that are in the map. First posted on arXiv 11 Feb 2026.

Builds on

23 of 73 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data9 Jun
  2. 2025R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation7 Apr
  3. 2025Reasoning with LLMs for Zero-Shot Vulnerability Detection22 Mar
  4. 2024To Err is Machine: Vulnerability Detection Challenges LLM Reasoning25 Mar
  5. 2024An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors29 Jan
  6. 2024LLM4Vuln: A Unified Evaluation Framework for Decoupling and Enhancing LLMs' Vulnerability Reasoning29 Jan

Other references · 17

  1. 2024Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaborationcited by 176
  2. 2024Vulnerability Detection with Code Language Models: How Far Are We?cited by 133
  3. 2024IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilitiescited by 100
  4. 2024Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAGcited by 67
  5. 2023A Multi-Task Embedder For Retrieval Augmented LLMscited by 63
  6. 2023How Far Have We Gone in Vulnerability Detection Using Large Language Modelscited by 27
  7. 2024Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphscited by 24
  8. 2024Comparison of Static Application Security Testing Tools and Large Language Models for Repo-level Vulnerability Detectioncited by 18
  9. 2025SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Codecited by 17
  10. 2024Investigating Large Language Models for Code Vulnerability Detection: An Experimental Studycited by 11
  11. 2024LProtector: An LLM-driven Vulnerability Detection Systemcited by 8
  12. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoningcited by 8
5 more
  1. 2018VulDeePecker: A Deep Learning-Based System for Vulnerability Detectioncited by 4
  2. 2023Benchmarking Software Vulnerability Detection Techniques: A Surveycited by 4
  3. 2025Assessing the Impact of Code Changes on the Fault Localizability of Large Language Modelscited by 4
  4. 2024Code Vulnerability Detection: A Comparative Analysis of Emerging Large Language Modelscited by 3
  5. 2025Learning to Focus: Context Extraction for Efficient Code Vulnerability Detection with Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection
  2. 2025VulInstruct: Teaching LLMs Root-Cause Reasoning for Vulnerability Detection via Security Specifications
  3. 2026Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection
  4. 2026VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection
  5. 2025VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
  6. 2026Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap
  7. 2026ConceptCoder: Improve Code Reasoning via Concept Learning
  8. 2024Towards Explainable Vulnerability Detection with Large Language Models