NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912684590497792 |
|---|---|
| author | Li, Yilin Meng, Guozhu Sun, Mingyang Wang, Yanzhong Sun, Kun Chang, Hailong Li, Yuekang |
| author_facet | Li, Yilin Meng, Guozhu Sun, Mingyang Wang, Yanzhong Sun, Kun Chang, Hailong Li, Yuekang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06402 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables Li, Yilin Meng, Guozhu Sun, Mingyang Wang, Yanzhong Sun, Kun Chang, Hailong Li, Yuekang Machine Learning Cryptography and Security 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. |
| title | NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2509.06402 |