一句话：提出 CodeInverter 套件，用 CFG 与数据映射增强 LLM 反编译，并发布数据集与轻量模型。
二进制反编译对网络安全与软件工程至关重要。现有 LLM 端到端方法虽能生成较可读源码，但在程序结构与逻辑重建、数据恢复、隐私和效率上仍不足。本文提出 CodeInverter Suite：CIW 提示工程将控制流图与显式数据映射融入提示，增强结构重建和数据恢复；CID 是含 869 万样本的大规模领域数据集，附带 CFG 和数据映射；CIM 为 1.3B 与 6.7B 轻量模型，适合隐私敏感和资源受限环境。实验显示 CIW 平均提升可重执行性 13.07%、可重编译性 23.94%；CIM-6.7B 在可重执行性和可读性上达 SOTA，分别超过参数量大百倍的模型 11.03% 和 6.27%。
Binary decompilation plays a vital role in various cybersecurity and software engineering tasks. Recently, end-to-end decompilation methods powered by large language models (LLMs) have attracted increasing attention for their ability to generate highly readable source code with minimal human intervention. However, existing LLM-based methods still struggle with reconstructing program structure and logic, achieving accurate data recovery, ensuring data security and privacy, and maintaining computational efficiency. To address these challenges, we propose the CodeInverter Suite, with three main pieces: (1) the CodeInverter Workflow (CIW) is a novel prompt engineering method that incorporates control flow graphs (CFG) and explicit data mappings to enhance structure reconstruction and data recovery during decompilation; (2) building upon CIW, we construct the CodeInverter Dataset (CID), a large-scale domain-specific dataset containing 8.69 million samples enriched with CFGs and data mapping information; (3) we develop CodeInverter Models (CIMs), two lightweight LLMs with 1.3B and 6.7B parameters, enabling efficient inference in privacy-sensitive and resource-constrained environments. Extensive experiments on two benchmark datasets demonstrate that CIW significantly enhances the decompilation performance of various LLMs, with average improvements of 13.07% in re-executability and 23.94% in re-compilability. For our proposed decompilation model, CIM-6.7B achieves state-of-the-art performance in terms of re-executability and readability, outperforming existing LLMs—even with over 100× more parameters—by an average of 11.03% and 6.27%, respectively.
@inproceedings{paperbot12490,
title = {The CodeInverter Suite: Structure- and Data-Aware Binary Decompilation with Efficient LLMs},
author = {Peipei Liu and Jian Sun and Rongkang Sun and Li Chen and Zhaoteng Yan and Xiaoling Zhang and Dawei Wang and Dapeng Sun and Peizheng Zhang and Dan Li},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3837554}
}