EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reframing Paths as Logic: Semantic Segmentation for Vulnerability Detection

Zong Cao, Yuqiang Sun, Zhengzi Xu, Kaixuan Li, Yeqi Fu, Yiran Zhang, Ziqiao Kong, Yang Liu

Proceedings of the ACM on Programming Languages · 10.04.2026 · 10 (OOPSLA1) · 1989-2016

DOI: 10.1145/3798272 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Programming Languages, online erschienen am 10.04.2026. Verfasst von Zong Cao und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Research Foundation, Singapore, and DSO National Laboratories under the AI Singapore Programme, the National Research Foundation Singapore and the Cyber Security Agency under the National Cybersecurity R&D Programme, the National Research Foundation, Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Path-sensitive vulnerabilities, such as use-after-free, integer overflows, and command injection, pose significant challenges for traditional static analysis tools, which often face trade-offs between precision, scalability, and interpretability. To address these challenges, we present SEVDF (Semantic-Enhanced Vulnerability Detection Framework), a novel methodology that integrates may-analysis taint propagation with large language models (LLMs) to detect path-related vulnerabilities in large C/C++ codebases. SEVDF begins by constructing a program dependency graph and performing a sound but incomplete taint analysis to extract all potential vulnerable paths. After segmentation, deduplication, feasibility check, and semantic summarization by LLMs, the vulnerable paths are reformed and confirmed with LLMs for their inter-procedural feasibility and semantic consistency. We evaluate SEVDF on the Juliet Test Suite (thirteen CWE categories) and a curated real-world dataset of 71 vulnerabilities across 9 projects. SEVDF consistently outperforms the default CodeQL rules, CodeQL rules with all unnecessary constraints removed, and three open-source detectors, which are Infer, Cppcheck and CodeChecker. SEVDF is able to achieve 100% precision on several CWEs while maintaining or improving recall on Juliet benchmark. Moreover, our segment-based design reduces the analysis workload for LLMs by 90.6% compared to direct-path prompting through Logic Unit deduplication, making SEVDF cost-effective for large-scale deployment. Finally, SEVDF uncovered and reported 29 0-day vulnerabilities (12 confirmed to date), including 3 CVEs in VirtualBox, demonstrating practical value.

Förderung

  • the National Research Foundation, Singapore, and DSO National Laboratories under the AI Singapore Programme
  • the National Research Foundation Singapore and the Cyber Security Agency under the National Cybersecurity R&D Programme
  • the National Research Foundation, Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme
  • IE2025 Industry Alignment Fund – Industry Collaboration Projects (IAF-ICP) Funding Initiative

Zitieren

APA

Cao, Z., Sun, Y., Xu, Z., Li, K., Fu, Y., Zhang, Y., Kong, Z., & Liu, Y. (2026). Reframing Paths as Logic: Semantic Segmentation for Vulnerability Detection. Proceedings of the ACM on Programming Languages, 10(OOPSLA1), 1989-2016. https://doi.org/10.1145/3798272

Vancouver

Cao Z, Sun Y, Xu Z, Li K, Fu Y, Zhang Y, et al. Reframing Paths as Logic: Semantic Segmentation for Vulnerability Detection. Proceedings of the ACM on Programming Languages. 2026;10(OOPSLA1):1989-2016. doi:10.1145/3798272

BibTeX
@article{Cao2026,
  author = {Cao, Zong and Sun, Yuqiang and Xu, Zhengzi and Li, Kaixuan and Fu, Yeqi and Zhang, Yiran and Kong, Ziqiao and Liu, Yang},
  title = {Reframing Paths as Logic: Semantic Segmentation for Vulnerability Detection},
  journal = {Proceedings of the ACM on Programming Languages},
  year = {2026},
  volume = {10},
  number = {OOPSLA1},
  pages = {1989--2016},
  doi = {10.1145/3798272}
}
Kostenlos starten →