Towards Secure Program Partitioning for Smart Contracts With LLM’s In-Context Learning
IEEE Transactions on Software Engineering · 2026-04 · 52 (4) · 1549-1567
DOI: 10.1109/tse.2026.3668858 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Software Engineering, 2026-04. Verfasst von Ye Liu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 90 Literaturangaben. Gefördert von: National Research Foundation, Singapore, and the Cyber Security Agency of Singapore through the National Cybersecurity R&D Programme.
Abstract (Originalsprache)
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information. Addressing manipulation vulnerabilities is particularly challenging because they stem from inherent data confidentiality issues rather than straightforward implementation bugs. To tackle this by preventing sensitive information leakage, we present PartitionGPT, the first LLM-driven approach that combines static analysis with the in-context learning capabilities of large language models (LLMs) to partition smart contracts into critical (privileged) and normal codebases, guided by a few annotated sensitive data variables. We evaluated PartitionGPT on 18 annotated smart contracts containing 99 sensitive functions. The results demonstrate that PartitionGPT successfully generates compilable, and verified partitions, achieving a precision of 80% while reducing more than 26% code compared to function-level partitioning approach. Furthermore, we evaluated PartitionGPT on nine real-world manipulation attacks that led to a total loss of 25 million dollars, PartitionGPT effectively prevents eight cases, highlighting its potential for broad applicability and the necessity for secure program partitioning during smart contract development to diminish manipulation vulnerabilities.
Förderung
- National Research Foundation, Singapore, and the Cyber Security Agency of Singapore through the National Cybersecurity R&D Programme
Zitieren
APA
Liu, Y., Niu, Y., Ma, C., Han, R., Ma, W., Li, Y., Gao, D., & Lo, D. (2026). Towards Secure Program Partitioning for Smart Contracts With LLM’s In-Context Learning. IEEE Transactions on Software Engineering, 52(4), 1549-1567. https://doi.org/10.1109/tse.2026.3668858
Vancouver
Liu Y, Niu Y, Ma C, Han R, Ma W, Li Y, et al. Towards Secure Program Partitioning for Smart Contracts With LLM’s In-Context Learning. IEEE Transactions on Software Engineering. 2026;52(4):1549-1567. doi:10.1109/tse.2026.3668858
BibTeX
@article{Liu2026,
author = {Liu, Ye and Niu, Yuqing and Ma, Chengyan and Han, Ruidong and Ma, Wei and Li, Yi and Gao, Debin and Lo, David},
title = {Towards Secure Program Partitioning for Smart Contracts With LLM’s In-Context Learning},
journal = {IEEE Transactions on Software Engineering},
year = {2026},
volume = {52},
number = {4},
pages = {1549--1567},
doi = {10.1109/tse.2026.3668858}
}
EUVIMED