# NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables

arXiv: https://arxiv.org/abs/2509.06402 · HTML: https://mlsanity.com/paper/2509.06402/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 64 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Backdoor Learning: A Survey](https://mlsanity.com/paper/2007.08745/) (2020)
- [Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution](https://mlsanity.com/paper/1608.01041/) (2016)
- [Dynamic Backdoor Attacks Against Machine Learning Models](https://mlsanity.com/paper/2003.03675/) (2020)
- [Glow: Graph Lowering Compiler Techniques for Neural Networks](https://mlsanity.com/paper/1805.00907/) (2018)
- [NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision](https://mlsanity.com/paper/1810.10090/) (2018)
- [The Deep Learning Compiler: A Comprehensive Survey](https://mlsanity.com/paper/2002.03794/) (2020)
- [HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation](https://mlsanity.com/paper/2412.21199/) (2024)
- [Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Apps](https://mlsanity.com/paper/2002.07687/) (2020)
- [CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?](https://mlsanity.com/paper/2408.10718/) (2024)
- [Refining Decompiled C Code with Large Language Models](https://mlsanity.com/paper/2310.06530/) (2023)
- [Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Apps](https://mlsanity.com/paper/2101.04401/) (2021)
- [Understanding Real-world Threats to Deep Learning Models in Android Apps](https://mlsanity.com/paper/2209.09577/) (2022)
- [Smart App Attack: Hacking Deep Learning Models in Android Apps](https://mlsanity.com/paper/2204.11075/) (2022)
- [Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineering](https://mlsanity.com/paper/2406.06637/) (2024)
- [Decompiling x86 Deep Neural Network Executables](https://mlsanity.com/paper/2210.01075/) (2022)
- [How Far Have We Gone in Binary Code Understanding Using Large Language Models](https://mlsanity.com/paper/2404.09836/) (2024)
- [Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binaries](https://mlsanity.com/paper/2411.04981/) (2024)

## Abstract (arXiv)

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.