Logo image
Back
Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation
Conference proceeding   Open access

Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation

Shangqing Liu, Wei Ma, Jian Wang, Xiaofei Xie, Ruitao Feng and Yang Liu
Proceedings of the 25th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems, pp.166-177
ACM Conferences
LCTES '24: ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems, 25th (Copenhagen, Denmark, 24/06/2024)
06/2024
DOI: https://doi.org/10.1145/3652032.3657564
Appears in  Recent Faculty of Science and Engineering Publications
pdf
Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data Augmentation339.73 kBDownloadView
Published (Version of record)CC BY V4.0,  Open Access
url
Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data AugmentationView
Published (Version of record)CC BY V4.0,  Open

Related links

Metrics

3 File views/ downloads
37 Record Views
9 Times Cited - Web of Science

Abstract

Graph Neural Networks Vulnerability Detection
Source code vulnerability detection aims to identify inherent vulnerabilities to safeguard software systems from potential attacks. Many prior studies overlook diverse vulnerability characteristics, simplifying the problem into a binary (0-1) classification task for example determining whether it is vulnerable or not. This poses a challenge for a single deep-learning based model to effectively learn the wide array of vulnerability characteristics. Furthermore, due to the challenges associated with collecting large-scale vulnerability data, these detectors often overfit limited training datasets, resulting in lower model generalization performance. To address the aforementioned challenges, in this work, we introduce a fine-grained vulnerability detector namely FGVulDet. Unlike previous approaches, FGVulDet employs multiple classifiers to discern characteristics of various vulnerability types and combines their outputs to identify the specific type of vulnerability. Each classifier is designed to learn type-specific vulnerability semantics. Additionally, to address the scarcity of data for some vulnerability types and enhance data diversity for learning better vulnerability semantics, we propose a novel vulnerability-preserving data augmentation technique to augment the number of vulnerabilities. Taking inspiration from recent advancements in graph neural networks for learning program semantics, we incorporate a Gated Graph Neural Network (GGNN) and extend it to an edge-aware GGNN to capture edge-type information. FGVulDet is trained on a large-scale dataset from GitHub, encompassing five different types of vulnerabilities. Extensive experiments compared with static-analysis-based approaches and learning-based approaches have demonstrated the effectiveness of FGVulDet.

Details

Logo image