EUVIMEDEUVIMED entdecken
Crossref

Weakly Supervised Vulnerability Localization via Multiple Instance Learning

Wenchao Gu, Yupan Chen, Yanlin Wang, Hongyu Zhang, Cuiyun Gao, Michael R. Lyu

ACM Transactions on Software Engineering and Methodology · 31.07.2026 · 35 (7) · 1-31

DOI: 10.1145/3768572 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 17.06.2026. Verfasst von Wenchao Gu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Gefördert von: Research Grants Council Grant for Theme-based Research Scheme Project, National Natural Science Foundation of China under project, Natural Science Foundation of Guangdong Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Software vulnerability detection has emerged as a significant concern in the field of software security recently, capturing the attention of numerous researchers and developers. Most previous approaches focus on coarse-grained vulnerability detection, such as at the function or file level. However, the developers would still encounter the challenge of manually inspecting a large volume of code inside the vulnerable function to identify the specific vulnerable statements for modification, indicating the importance of vulnerability localization. Training the model for vulnerability localization usually requires ground-truth labels at the statement-level, and labeling vulnerable statements demands expert knowledge, which incurs high costs. Hence, the demand for an approach that eliminates the need for additional labeling at the statement-level is on the rise. To tackle this problem, we propose a novel approach called WAVES for W e A kly supervised V ulnerability Localization via multipl E in S tance learning, which does not need the additional statement-level labels during the training. WAVES has the capability to determine whether a function is vulnerable (i.e., vulnerability detection) and pinpoint the vulnerable statements (i.e., vulnerability localization). Specifically, inspired by the concept of multiple instance learning, WAVES converts the ground-truth label at the function-level into pseudo labels for individual statements, eliminating the need for additional statement-level labeling. These pseudo labels are utilized to train the classifiers for the function-level representation vectors. Extensive experimentation on three popular benchmark datasets demonstrates that, in comparison to previous baselines, our approach achieves comparable performance in vulnerability detection and state-of-the-art performance in statement-level vulnerability localization.

Förderung

  • Research Grants Council Grant for Theme-based Research Scheme Project
  • National Natural Science Foundation of China under project
  • Natural Science Foundation of Guangdong Province

Zitieren

APA

Gu, W., Chen, Y., Wang, Y., Zhang, H., Gao, C., & Lyu, M. R. (2026). Weakly Supervised Vulnerability Localization via Multiple Instance Learning. ACM Transactions on Software Engineering and Methodology, 35(7), 1-31. https://doi.org/10.1145/3768572

Vancouver

Gu W, Chen Y, Wang Y, Zhang H, Gao C, Lyu MR. Weakly Supervised Vulnerability Localization via Multiple Instance Learning. ACM Transactions on Software Engineering and Methodology. 2026;35(7):1-31. doi:10.1145/3768572

BibTeX
@article{Gu2026,
  author = {Gu, Wenchao and Chen, Yupan and Wang, Yanlin and Zhang, Hongyu and Gao, Cuiyun and Lyu, Michael R.},
  title = {Weakly Supervised Vulnerability Localization via Multiple Instance Learning},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {7},
  pages = {1--31},
  doi = {10.1145/3768572}
}
Kostenlos starten →