.png){kind=icon}
Return
Vulnerability Detection via Multiple-Graph-Based Code Representation
.png){kind=icon}
PRE
AI
DOI：10.1109/TSE.2024.3427815.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
During software development and maintenance, vulnerability detection is an essential part of software quality assurance. Even though many program-analysis-based and machine-learning-based approaches have been proposed to automatically detect vulnerabilities, they rely on explicit rules or patterns defined by security experts and suffer from either high false positives or high false negatives. Recently, an increasing number of studies leverage deep learning techniques, especially Graph Neural Network (GNN), to detect vulnerabilities. These approaches leverage program analysis to represent the program semantics as graphs and perform graph analysis to detect vulnerabilities. However, they suffer from two main problems: (i) Existing GNN-based techniques do not effectively learn the structural and semantic features from source code for vulnerability detection. (ii) These approaches tend to ignore fine-grained information in source code. To tackle these problems, in this paper, we propose a novel vulnerability detection approach, named MGVD (MULTIPLE-GRAPH-BASED VULNERABILITY DETECTION), to detect vulnerable functions. To effectively learn the structural and semantic features from source code, MGVD uses three different ways to represent each function into multiple forms, i.e., two statement graphs and a sequence of tokens. Then we encode such representations to a three-channel feature matrix. The feature matrix contains the structural feature and the semantic feature of the function. And we add a weight allocation layer to distribute the weights between structural and semantic features. To overcome the second problem, MGVD constructs each graph representation of the input function using multiple different graphs instead of a single graph. Each graph focuses on one statement in the function and its nodes denote the related statements and their fine-grained code elements. Finally, MGVD leverages CNN to identify whether this function is vulnerable based on such feature matrix. We conduct experiments on 3 vulnerability datasets with a total of 30,341 vulnerable functions and 127,931 non-vulnerable functions. The experimental results show that our method outperforms the state-of-the-art by 9.68% - 10.28% in terms of F1-score.
Keywords:
Semantics
Codes
Source coding
Graph neural networks
Software
Feature extraction
Deep learning
Vulnerability detection
deep learning
code representation
graph neural network
Journal
IF:
5.6
Papers:
2.9K
Citations:
1.1W
Organization
Cited Papers
ShareSaveStructure and Mechanical Properties of Ti-Al-Ta-N Coatings Deposited by Direct Current and Middle-Frequency Magnetron Sputtering.png)
Metals
OAAI
MetalsIF0
OAAIShareSave
ShareSaveShareSaveDevelopment of a Test System for Mutagenicity of Photosensitizers Using Drosophila melanogaster¶
PREAI
ShareSave
View more