用大模型+动态分析，逆向还原深度学习模型执行文件
NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables
- 结合大模型语义理解与动态分析，识别算子类型和属性
- 非量化模型还原接近原貌，量化模型保持72%准确率
- 适合安全研究者逆向分析边缘设备模型
在设备端部署的深度学习模型需求广泛，编译器将模型高效编译为可执行文件，但面临逆向工程威胁。此前研究在处理编译优化和量化模型分析时存在困难。本文提出NeuroDeX，利用大语言模型（LLM）的语义理解能力与动态分析，实现算子类型识别、属性恢复和模型重建，可还原经编译优化、不同架构及量化处理的DNN可执行文件。我们在12种常见DNN模型上的96个可执行文件上进行实验，结果表明：对于非量化可执行文件，NeuroDeX能还原出几乎完全相同的高层模型；对于量化模型，可恢复功能相似的高层模型，平均顶1准确率达72%。相比现有方法，NeuroDeX提供了更全面有效的解决方案。
原文摘要 · Abstract (English)
On-device deep learning models have extensive real world demands. Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these executables may face the threat of reverse engineering. Previous studies have attempted to decompile DNN executables, but they face challenges in handling compilation optimizations and analyzing quantized compiled models. In this paper, we present NeuroDeX to unlock diverse support in decompiling DNN executables. NeuroDeX leverages the semantic understanding capabilities of LLMs along with dynamic analysis to accurately and efficiently perform operator type recognition, operator attribute recovery and model reconstruction. NeuroDeX can recover DNN executables into high-level models towards compilation optimizations, different architectures and quantized compiled models. We conduct experiments on 96 DNN executables across 12 common DNN models. Extensive experimental results demonstrate that NeuroDeX can decompile non-quantized executables into nearly identical high-level models. NeuroDeX can recover functionally similar high-level models for quantized executables, achieving an average top-1 accuracy of 72%. NeuroDeX offers a more comprehensive and effective solution compared to previous DNN executables decompilers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。