Empowering IoT Security: Automated Identification of Standard Library Functions in RTOS Firmware With LLM and RAG
IEEE Internet of Things Journal · 01.06.2026 · 13 (11) · 23876-23889
DOI: 10.1109/jiot.2026.3670949 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 01.06.2026. Verfasst von Zhihan Zheng und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
Reverse engineering embedded firmware for real-time operating systems (RTOSs) is a formidable challenge in Internet of Things security. The common practice of stripping symbolic information from firmware to optimize performance and storage makes identifying standard library functions exceptionally difficult, creating a significant bottleneck for functional analysis and vulnerability discovery. This article introduces a novel, automated method for identifying these functions in RTOS firmware by leveraging large language models (LLMs). Our approach operates directly on raw binary code, requiring no symbolic or debugging information, and demonstrates broad generalizability across diverse hardware architectures and compilers. At its core, the method combines retrieval-augmented generation (RAG) to enhance identification accuracy with a newly designed adaptive iterative screening algorithm (AISA), which optimizes analysis efficiency by prioritizing candidate functions based on a weighted score of call frequency, call depth, and address proximity to reduce token costs. We validated our method through rigorous experimentation on Zephyr RTOS firmware spanning nine architectures (e.g., ARM, MIPS, RISC-V). The results are compelling: our approach achieves a 90.59% accuracy rate in identifying standard library function names. Moreover, its application to commercial Internet of Things (IoT) firmware confirms its high efficiency, identifying functions significantly faster and more economically than traditional heuristic techniques. This work contributes a powerful, general-purpose, and cost-effective solution for automated firmware analysis.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
Zitieren
APA
Zheng, Z., Tan, Y., Chen, Z., Lu, Z., Meng, W., & Wang, S. (2026). Empowering IoT Security: Automated Identification of Standard Library Functions in RTOS Firmware With LLM and RAG. IEEE Internet of Things Journal, 13(11), 23876-23889. https://doi.org/10.1109/jiot.2026.3670949
Vancouver
Zheng Z, Tan Y, Chen Z, Lu Z, Meng W, Wang S. Empowering IoT Security: Automated Identification of Standard Library Functions in RTOS Firmware With LLM and RAG. IEEE Internet of Things Journal. 2026;13(11):23876-23889. doi:10.1109/jiot.2026.3670949
BibTeX
@article{Zheng2026,
author = {Zheng, Zhihan and Tan, Yu-an and Chen, Zihan and Lu, Zheng and Meng, Weizhi and Wang, Shuo},
title = {Empowering IoT Security: Automated Identification of Standard Library Functions in RTOS Firmware With LLM and RAG},
journal = {IEEE Internet of Things Journal},
year = {2026},
volume = {13},
number = {11},
pages = {23876--23889},
doi = {10.1109/jiot.2026.3670949}
}
EUVIMED