EUVIMEDEUVIMED entdecken
Crossref

Energy-Efficient LLM-Based Decompilation via a Two-Stage Pipeline on Constrained Hardware

Rodolphe Picot, Ahmad Shahnejat Bushehri, Felipe Gohring de Magalhaes, Maroua Ben Atti, Alejandro Quintero, Gabriela Nicolescu

ACM Transactions on Embedded Computing Systems · 02.07.2026

DOI: 10.1145/3829084 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Embedded Computing Systems, online erschienen am 02.07.2026. Verfasst von Rodolphe Picot und 5 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in large language models (LLMs) have enabled substantial progress in decompiling binary executables. Yet, current approaches remain highly resource-intensive and mainly target single-function programs. In this work, we present a lightweight two-stage decompilation pipeline designed to operate on constrained hardware while extending LLM-based decompilation to multi-function programs. We construct a new dataset of synthetic yet structurally diverse C programs and their corresponding assembly code, generated using two distinct LLMs to enforce a deliberate distributional shift between the training and testing data. Our system relies on a fine-tuned 7B-parameter model for primary decompilation and a secondary, inference-only 24B-parameter correction model for targeted compilation-error repair, enabling efficient processing under strict memory and compute constraints. To enable a direct comparison with prior work, we adapt the LLM4Decompile framework for multi-function settings by automatically reconstructing unified headers while preserving cross-function dependencies. Experimental evaluations using AST similarity, lexical similarity, compilation rate, and execution similarity show that our method achieves competitive structural and textual fidelity while surpassing LLM4Decompile baselines in compilation and execution success, despite operating on commodity-class hardware. Moreover, we demonstrate that our approach reduces energy consumption by 85% compared to existing refine-based methods, making it highly suitable for sustainable deployment in resource-constrained environments.

Zitieren

APA

Picot, R., Bushehri, A. S., Magalhaes, F. G. D., Atti, M. B., Quintero, A., & Nicolescu, G. (2026). Energy-Efficient LLM-Based Decompilation via a Two-Stage Pipeline on Constrained Hardware. ACM Transactions on Embedded Computing Systems. https://doi.org/10.1145/3829084

Vancouver

Picot R, Bushehri AS, Magalhaes FGD, Atti MB, Quintero A, Nicolescu G. Energy-Efficient LLM-Based Decompilation via a Two-Stage Pipeline on Constrained Hardware. ACM Transactions on Embedded Computing Systems. 2026. doi:10.1145/3829084

BibTeX
@article{Picot2026,
  author = {Picot, Rodolphe and Bushehri, Ahmad Shahnejat and Magalhaes, Felipe Gohring de and Atti, Maroua Ben and Quintero, Alejandro and Nicolescu, Gabriela},
  title = {Energy-Efficient LLM-Based Decompilation via a Two-Stage Pipeline on Constrained Hardware},
  journal = {ACM Transactions on Embedded Computing Systems},
  year = {2026},
  doi = {10.1145/3829084}
}
Kostenlos starten →