郑州大学学报（理学版）2026，Vol.58Issue(1)：19-26,8.DOI:10.13705/j.issn.1671-6841.2024119
一种融合双曲表示与欧几里得表示的源代码漏洞检测方法
A Source Code Vulnerability Detection Method Fusing Hyperbolic Representation and Euclidean Representation
摘要
Abstract
With the increasing complexity of software systems,source code vulnerability detection has be-come a key task to maintain software security.Although various vulnerability detection methods based on deep learning were proposed,they mainly relied on a single Euclidean space perspective to extract the se-mantic features and structural features in the code representation structure,which limited their ability to detect vulnerabilities hidden deep in the code.In order to solve this limitation,VulDEHGCN,a source code vulnerability detection method fusing hyperbolic representation and euclidean representation was pro-posesed.It could embedd the source code from two different spaces,so as to mine the vulnerability char-acteristics of the source code from different perspectives,so as to achieve more accurate vulnerability de-tection.The experimental results showed that compared with the existing vulnerability detection methods,VulDEHGCN achieved significant improvement in key performance indicators such as accuracy,preci-sion,recall and F1 score.The accuracy and F1 score reached 98.93%and 96.63%respectively.Abla-tion studies also confirm the superiority of fusing code embeddings from different perspectives to further enhance vulnerability detection performance.关键词
漏洞检测/切片级别/双曲空间/欧氏空间/融合表示Key words
vulnerability detection/slice-level/hyperbolic space/Euclidean space/fused representa-tion分类
信息技术与安全科学引用本文复制引用
陈旭,陈子雄,景永俊,王叔洋,宋吉飞..一种融合双曲表示与欧几里得表示的源代码漏洞检测方法[J].郑州大学学报（理学版）,2026,58(1):19-26,8.基金项目
北方民族大学中央高校基本科研业务费专项资金(2023ZRLG13) （2023ZRLG13）
宁夏回族自治区重点研发项目(2023BDE02017) （2023BDE02017）
