Skip to main navigation Skip to search Skip to main content

Repository-Level Graph Representation Learning for Enhanced Security Patch Detection

  • Xin Cheng Wen
  • , Zirui Lin
  • , Cuiyun Gao*
  • , Hongyu Zhang
  • , Yong Wang
  • , Qing Liao
  • *Corresponding author for this work
  • Harbin Institute of Technology Shenzhen
  • Peng Cheng Laboratory
  • Chongqing University
  • Anhui Polytechnic University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Software vendors often silently release security patches without providing sufficient advisories (e.g., Common Vulnerabilities and Exposures) or delayed updates via resources (e.g., National Vulnerability Database). Therefore, it has become crucial to detect these security patches to ensure secure software maintenance. However, existing methods face the following challenges: (1) They primarily focus on the information within the patches themselves, overlooking the complex dependencies in the repository. (2) Security patches typically involve multiple functions and files, increasing the difficulty in well learning the representations. To alleviate the above challenges, this paper proposes a Repository-level Security Patch Detection framework named RepoSPD, which comprises three key components: 1) a repository-level graph construction, RepoCPG, which represents software patches by merging pre-patch and post-patch source code at the repository level; 2) a structure-aware patch representation, which fuses the graph and sequence branch and aims at comprehending the relationship among multiple code changes; 3) progressive learning, which facilitates the model in balancing semantic and structural information. To evaluate RepoSPD, we employ two widely-used datasets in security patch detection: SPI-DB and PatchDB. We further extend these datasets to the repository level, incorporating a total of 20,238 and 28,781 versions of repository in C/C++ programming languages, respectively, denoted as SPI-DB∗ and PatchDB*. We compare RepoSPD with six existing security patch detection methods and five static tools. Our experimental results demonstrate that RepoSPD outperforms the state-of-the-art baseline, with improvements of 11.90%, and 3.10% in terms of accuracy on the two datasets, respectively. These results underscore the effectiveness of RepoSPD in detecting security patches. Furthermore, RepoSPD can detect 151 security patches, which outperforms the best-performing baseline by 21.36% with respect to accuracy.

Original languageEnglish
Title of host publicationProceedings - 2025 IEEE/ACM 47th International Conference on Software Engineering, ICSE 2025
PublisherIEEE Computer Society
Pages2600-2612
Number of pages13
ISBN (Electronic)9798331505691
DOIs
StatePublished - 2025
Externally publishedYes
Event47th IEEE/ACM International Conference on Software Engineering, ICSE 2025 - Ottawa, Canada
Duration: 27 Apr 20253 May 2025

Publication series

NameProceedings - International Conference on Software Engineering
ISSN (Print)0270-5257

Conference

Conference47th IEEE/ACM International Conference on Software Engineering, ICSE 2025
Country/TerritoryCanada
CityOttawa
Period27/04/253/05/25

Keywords

  • deep learning
  • security patch detection

Fingerprint

Dive into the research topics of 'Repository-Level Graph Representation Learning for Enhanced Security Patch Detection'. Together they form a unique fingerprint.

Cite this