What is it about?
Software vulnerabilities pose a serious threat to people's lives and property safety, making it crucial to protect software security. In recent years, many approaches have employed deep learning to detect vulnerabilities in software code. However, they often overlook the rich, structured semantic information of the code. This study proposes a vulnerability-enriched code semantic graph, a novel graph-based code structure, to aid deep learning models in detecting software code vulnerabilities.
Featured Image
Photo by Iyus sugiharto on Unsplash
Why is it important?
This study proposes a vulnerability-enriched code semantic graph, a novel graph-based code structure, to aid deep learning models in detecting software code vulnerabilities.
Perspectives
This is a relatively novel research that can help you open up your mind. The vulnerability knowledge utilization part can bring you some inspiration.
Jiayuan Li
University of the Chinese Academy of Sciences
Read the Original
This page is a summary of: PVDetector: Pretrained Vulnerability Detection on Vulnerability-enriched Code Semantic Graph, ACM Transactions on Software Engineering and Methodology, September 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3768582.
You can read the full text:
Resources
Contributors
The following have contributed to this page
