EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

vul-rag : Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG

Xueying Du, Geng Zheng, Kaixin Wang, Yi Zou, Yujia Wang, Wentai Deng, Jiayi Feng, Mingwei Liu, Bihuan Chen, Xin Peng, Tao Ma, Yiling Lou

ACM Transactions on Software Engineering and Methodology · 31.10.2026 · 35 (10) · 1-25

DOI: 10.1145/3797277 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 16.09.2026. Verfasst von Xueying Du und 11 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 67 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)

Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched code (only 0.06–0.14 accuracy). It shows that LLMs struggle to capture the root causes of vulnerabilities during vulnerability detection. To address this challenge, we propose enhancing LLMs with multi-dimensional vulnerability knowledge distilled from historical vulnerabilities and fixes. We design a novel knowledge-level Retrieval-Augmented Generation framework Vul-RAG , which improves LLMs with an accuracy increase of 16–24% in identifying vulnerable and patched code. Additionally, vulnerability knowledge generated by Vul-RAG can further (1) serve as high-quality explanations to improve manual detection accuracy (from 60% to 77%), and (2) detect 10 previously-unknown bugs in the recent Linux kernel release with six assigned CVEs.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Du, X., Zheng, G., Wang, K., Zou, Y., Wang, Y., Deng, W., Feng, J., Liu, M., Chen, B., Peng, X., Ma, T., & Lou, Y. (2026). vul-rag : Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG. ACM Transactions on Software Engineering and Methodology, 35(10), 1-25. https://doi.org/10.1145/3797277

Vancouver

Du X, Zheng G, Wang K, Zou Y, Wang Y, Deng W, et al. vul-rag : Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG. ACM Transactions on Software Engineering and Methodology. 2026;35(10):1-25. doi:10.1145/3797277

BibTeX
@article{Du2026,
  author = {Du, Xueying and Zheng, Geng and Wang, Kaixin and Zou, Yi and Wang, Yujia and Deng, Wentai and Feng, Jiayi and Liu, Mingwei and Chen, Bihuan and Peng, Xin and Ma, Tao and Lou, Yiling},
  title = {vul-rag : Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {10},
  pages = {1--25},
  doi = {10.1145/3797277}
}
Kostenlos starten →