mlsanityData to 14 Oct 2026

NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables

arXiv 2509.06402 ↗First posted 8 Sep 2025cs.LG cs.CRcited by 0

Not on the map. Why?

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.

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

33 of 64 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  7. 2014Going Deeper with Convolutionscited by 4,241
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  9. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  10. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  11. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  12. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
21 more
  1. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  2. 2020Backdoor Learning: A Surveycited by 426
  3. 2016Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distributioncited by 158
  4. 2020Dynamic Backdoor Attacks Against Machine Learning Modelscited by 151
  5. 2018Glow: Graph Lowering Compiler Techniques for Neural Networkscited by 75
  6. 2018NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Visioncited by 68
  7. 2020The Deep Learning Compiler: A Comprehensive Surveycited by 46
  8. 2024HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generationcited by 39
  9. 2020Mind Your Weight(s): A Large-scale Study on Insufficient Machine Learning Model Protection in Mobile Appscited by 36
  10. 2024CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?cited by 30
  11. 2023Refining Decompiled C Code with Large Language Modelscited by 24
  12. 2021Robustness of on-device Models: Adversarial Attack to Deep Learning Models on Android Appscited by 19
  13. 2022Understanding Real-world Threats to Deep Learning Models in Android Appscited by 15
  14. 2022Smart App Attack: Hacking Deep Learning Models in Android Appscited by 12
  15. 2024Exploring the Efficacy of Large Language Models (GPT-4) in Binary Reverse Engineeringcited by 8
  16. 2022Decompiling x86 Deep Neural Network Executablescited by 7
  17. 2024How Far Have We Gone in Binary Code Understanding Using Large Language Modelscited by 7
  18. 2024Enhancing Reverse Engineering: Investigating and Benchmarking Large Language Models for Vulnerability Analysis in Decompiled Binariescited by 6
  19. 2024WaDec: Decompiling WebAssembly Using Large Language Modelcited by 5
  20. 2023Deploying Machine Learning Models to Ahead-of-Time Runtime on Edge Using MicroTVMcited by 3
  21. 2023A First Look at On-device Models in iOS Appscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models
  2. 2023Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables
  3. 2021SmartDeal: Re-Modeling Deep Network Weights for Efficient Inference and Training
  4. 2024DeepNcode: Encoding-Based Protection against Bit-Flip Attacks on Neural Networks
  5. 2022Graph-based Neural Modules to Inspect Attention-based Architectures: A Position Paper
  6. 2025Lobster: A GPU-Accelerated Framework for Neurosymbolic Programming
  7. 2022ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
  8. 2026SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side Channels