Detecting Code Vulnerabilities with Heterogeneous GNN Training
Preprint
- 16 May 2025
- preprint
- Published by Springer Nature in Research Square
Abstract
Detecting vulnerabilities in source code is a critical task for software security assurance. Graph Neural Network (GNN) machine learning can be a promising approach by modeling source code as graphs. Early approaches treated code elements uniformly, limiting their capacity to model diverse relationships that contribute to various vulnerabilities. Recent research addresses this limitation by considering the heterogeneity of node types and using Gated Graph Neural Networks (GGNN) to aggregate node information through different edge types. However, these edges primarily function as conduits for passing node information and may not capture detailed characteristics of distinct edge types. This paper presents Inter-Procedural Abstract Graphs (IPAGs) as an efficient, language-agnostic representation of source code, complemented by heterogeneous GNN training for vulnerability prediction. IPAGs capture the structural and contextual properties of code elements and their relationships. We also propose a Heterogeneous Attention GNN (HAGNN) model that incorporates multiple subgraphs capturing different features of source code. These subgraphs are learned separately and combined using a global attention mechanism, followed by a fully connected neural network for final classification. The proposed approach has achieved up to 96.6% accuracy on a large C dataset of 108 vulnerability types and 97.8% on a large Java dataset of 114 vulnerability types, outperforming state-of-the-art methods. Its applications to various real-world software projects have also demonstrated low false positive rates.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning2023
- Compact Abstract Graphs for Detecting Code Vulnerability with GNN Models | Proceedings of the 38th Annual Computer Security Applications Conference2022
- Detecting Integer Overflow Errors in Java Source Code via Machine Learning2021
- Combining Graph Neural Networks with Expert Knowledge for Smart Contract Vulnerability DetectionIEEE Transactions on Knowledge and Data Engineering, 2021
- SySeVR: A Framework for Using Deep Learning to Detect Software VulnerabilitiesIEEE Transactions on Dependable and Secure Computing, 2021
- Combining Graph-Based Learning With Automated Data Collection for Code Vulnerability DetectionIEEE Transactions on Information Forensics and Security, 2020
- Cross-Project Transfer Representation Learning for Vulnerable Function DiscoveryIEEE Transactions on Industrial Informatics, 2018
- Defect Prediction in Android Binary Executables Using Deep Neural NetworkWireless Personal Communications, 2017
- Predicting Vulnerable Software Components via Text MiningIEEE Transactions on Software Engineering, 2014
- Detection of malicious code by applying machine learning classifiers on static features: A state-of-the-art surveyInformation Security Technical Report, 2009