VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

TL;DR

VulTriage introduces a triple-path context augmentation framework that significantly improves LLM-based vulnerability detection by integrating structural, knowledge-based, and semantic information.

Contribution

The paper presents VulTriage, a novel framework that enhances LLM input with multiple context paths, leading to state-of-the-art vulnerability detection performance.

Findings

VulTriage outperforms existing baselines on PrimeVul dataset.

Each context path contributes significantly to detection accuracy.

The approach generalizes well to Kotlin and low-resource settings.

Abstract

Automated vulnerability detection is a fundamental task in software security, yet existing learning-based methods still struggle to capture the structural dependencies, domain-specific vulnerability knowledge, and complex program semantics required for accurate detection. Recent Large Language Models (LLMs) have shown strong code understanding ability, but directly prompting them with raw source code often leads to missed vulnerabilities or false alarms, especially when vulnerable and benign functions differ only in subtle semantic details. To address this, we propose VulTriage, a triple-path context augmentation framework for LLM-based vulnerability detection. VulTriage enhances the LLM input through three complementary paths: a Control Path that extracts and verbalizes AST, CFG, and DFG information to expose control and data dependencies; a Knowledge Path that retrieves relevant CWE-derived vulnerability patterns and examples through hybrid dense--sparse retrieval; and a Semantic Path that summarizes the functional behavior of the code before the final judgment. These contexts are integrated into a unified instruction to guide the LLM toward more reliable vulnerability reasoning. Experiments on the PrimeVul pair test set show that VulTriage achieves state-of-the-art performance, outperforming existing deep learning and LLM-based baselines on key pair-wise and classification metrics. Further ablation studies verify the effectiveness of each path, and additional experiments on the Kotlin dataset demonstrate the generalization ability of VulTriage under low-resource and class-imbalanced settings. Our code is available at https://github.com/vinsontang1/VulTriage