EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Recurring Vulnerability Detection: How Far Are We?

Yiheng Cao, Susheng Wu, Ruisi Wang, Bihuan Chen, Yiheng Huang, Chenhao Lu, Zhuotong Zhou, Xin Peng

Proceedings of the ACM on Software Engineering · 22.06.2025 · 2 (ISSTA) · 573-595

DOI: 10.1145/3728901 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 22.06.2025. Verfasst von Yiheng Cao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of open-source software, code reuse has become a common practice to accelerate development. However, it leads to inheritance from the original vulnerability, which recurs at the reusing projects, known as recurring vulnerabilities (RVs). Traditional general-purpose vulnerability detection approaches struggle with scalability and adaptability, while learning-based approaches are often constrained by limited training datasets and are less effective against unseen vulnerabilities. Though specific recurring vulnerability detection (RVD) approaches have been proposed, their effectiveness across various RV characteristics remains unclear. In this paper, we conduct a large-scale empirical study using a newly constructed RV dataset containing 4,569 RVs, achieving a 953% expansion over prior RV datasets. Our study analyzes the characteristics of RVs, evaluates the effectiveness of the state-of-the-art RVD approaches, and investigates the root causes of false positives and false negatives, yielding key insights. Inspired by these insights, we design A nt M an , a novel RVD approach that identifies both explicit and implicit call relations with modified functions, then employs inter-procedural taint analysis and intra-procedural dependency slicing within those functions to generate comprehensive signatures, and finally incorporates a flexible matching to detect RVs. Our evaluation has shown the effectiveness, generality and practical usefulness in RVD. A nt M an has detected 4,593 RVs, with 307 confirmed by developers, and identified 73 new 0-day vulnerabilities across 15 projects, receiving 5 CVE identifiers.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Cao, Y., Wu, S., Wang, R., Chen, B., Huang, Y., Lu, C., Zhou, Z., & Peng, X. (2025). Recurring Vulnerability Detection: How Far Are We?. Proceedings of the ACM on Software Engineering, 2(ISSTA), 573-595. https://doi.org/10.1145/3728901

Vancouver

Cao Y, Wu S, Wang R, Chen B, Huang Y, Lu C, et al. Recurring Vulnerability Detection: How Far Are We?. Proceedings of the ACM on Software Engineering. 2025;2(ISSTA):573-595. doi:10.1145/3728901

BibTeX
@article{Cao2025,
  author = {Cao, Yiheng and Wu, Susheng and Wang, Ruisi and Chen, Bihuan and Huang, Yiheng and Lu, Chenhao and Zhou, Zhuotong and Peng, Xin},
  title = {Recurring Vulnerability Detection: How Far Are We?},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2025},
  volume = {2},
  number = {ISSTA},
  pages = {573--595},
  doi = {10.1145/3728901}
}
Kostenlos starten →