EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching

Chengyan Ma, Jieke Shi, Ruidong Han, Ye Liu, Feng Li, Yuqing Niu, David Lo

Proceedings of the ACM on Software Engineering · 30.06.2026 · 3 (FSE) · 4551-4574

DOI: 10.1145/3808207 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 30.06.2026. Verfasst von Chengyan Ma und 6 weiteren Autor:innen. Die Arbeit nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation, Singapore, Cyber Security Agency of Singapore.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Trusted Execution Environments (TEEs) provide hardware-based isolation to protect sensitive data and computations from potentially compromised operating systems (OS). However, TEE applications inevitably interact with the untrusted OS through SDK interfaces, and improper partitioning can introduce severe vulnerabilities such as data leakage and code injection. While prior work has proposed static analysis tools to detect such issues, automated repair remains largely unexplored. This problem is particularly challenging due to three TEE-specific factors: the lack of standardized secure development guidelines, the difficulty of extracting semantic information from low-level C code, and the absence of mature testing and validation methods. In this work, we present TEERepair, a framework for automatically repairing bad partitioning issues in TEE applications. Our approach tackles the above challenges by introducing a domain-specific language (DSL) to encode repair rules that express and capture common TEE security patterns, which are instantiated as patch templates with placeholders for context-specific variables. We then leverage large language models (LLMs) to reason about code semantics and synthesize context-aware patches, and further generate test clients to validate the repairs. We evaluate TEERepair on the TEE Partitioning Errors Benchmark (PartitioningE-Bench), achieving a significantly higher repair success rate of 87.6% compared to baselines. Furthermore, applying TEERepair to real-world TEE projects, we submitted 5 repair pull requests, 2 of which have been confirmed and merged by project maintainers.

Förderung

  • National Research Foundation, Singapore
  • Cyber Security Agency of Singapore

Zitieren

APA

Ma, C., Shi, J., Han, R., Liu, Y., Li, F., Niu, Y., & Lo, D. (2026). Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching. Proceedings of the ACM on Software Engineering, 3(FSE), 4551-4574. https://doi.org/10.1145/3808207

Vancouver

Ma C, Shi J, Han R, Liu Y, Li F, Niu Y, et al. Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching. Proceedings of the ACM on Software Engineering. 2026;3(FSE):4551-4574. doi:10.1145/3808207

BibTeX
@article{Ma2026,
  author = {Ma, Chengyan and Shi, Jieke and Han, Ruidong and Liu, Ye and Li, Feng and Niu, Yuqing and Lo, David},
  title = {Automated Repair of TEE Partitioning Issues via DSL-Guided and LLM-Assisted Patching},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2026},
  volume = {3},
  number = {FSE},
  pages = {4551--4574},
  doi = {10.1145/3808207}
}
Kostenlos starten →