NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables

• URL: http://arxiv.org/abs/2509.06402v2
• Date: Mon, 03 Nov 2025 12:13:43 GMT
• Title: NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables
• Authors: Yilin Li, Guozhu Meng, Mingyang Sun, Yanzhong Wang, Kun Sun, Hailong Chang, Yuekang Li,
• Abstract summary: Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these executables may face the threat of reverse engineering.<n>Previous studies have attempted to decompile DNN executables, but they face challenges in handling compilation optimizations and analyzing quantized compiled models.<n>We present NeuroDeX to unlock diverse support in decompiling DNN executables.
• Score: 25.83684938915853
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code [52.66657751895655]
  Large Language Models (LLMs) offer a compelling new paradigm: Neural Compilation.<n>This paper introduces NeuComBack, a novel benchmark dataset specifically designed for IR-to-assembly compilation.<n>We propose a self-evolving prompt optimization method that enables LLMs to evolve their internal prompt strategies.
  arXiv  Detail & Related papers  (2025-11-03T03:20:26Z)
• A Tensor-Based Compiler and a Runtime for Neuron-Level DNN Certifier Specifications [4.681322438383984]
  We propose a compiler framework that translates neuron-level specifications of DNN certifiers into tensor-based, layer-level implementations.<n>This is enabled by a novel stack-based intermediate representation (IR) and a shape analysis that infers the implicit tensor operations needed to simulate the neuron-level semantics.<n>Using our compiler and g-BCSR, we make it easy to develop new certifiers and analyze their utility across diverse DNNs.
  arXiv  Detail & Related papers  (2025-07-26T20:38:29Z)
• Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables [18.123649165203652]
  Bit-flip attacks (BFAs) can manipulate deep neural networks (DNNs) For high-level DNN models running on deep learning (DL) frameworks like PyTorch, extensive BFAs have been used to flip bits in model weights and shown effective.
  arXiv  Detail & Related papers  (2023-09-12T13:42:20Z)
• DyCL: Dynamic Neural Network Compilation Via Program Rewriting and Graph Optimization [8.701484095864744]
  tool is a general approach that enables any existing DL compiler to successfully compile DyNNs. tool tackles the dynamic nature of DyNNs by converting a dynamic neural network into multiple sub-neural networks. compiled executables generated by tool exhibit significantly improved performance, running between $1.12times$ and $20.21times$ faster than the original DyNNs executed on general-purpose DL frameworks.
  arXiv  Detail & Related papers  (2023-07-11T01:53:19Z)
• oneDNN Graph Compiler: A Hybrid Approach for High-Performance Deep Learning Compilation [8.64220475114214]
  oneDNN Graph Compiler employs a hybrid approach of using techniques from both compiler optimization and expert-tuned kernels for high performance code generation. Experimental results demonstrate significant performance gains over existing tensor compiler and primitives library for performance-critical computation graphs.
  arXiv  Detail & Related papers  (2023-01-03T19:52:17Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Decompiling x86 Deep Neural Network Executables [20.91585339813852]
  BTD (Bin to DNN) is a decompiler for deep neural network (DNN) executables. We show that BTD can boost two representative attacks, adversarial example generation and knowledge stealing, against DNN executables.
  arXiv  Detail & Related papers  (2022-10-03T16:48:18Z)
• Sparse Flows: Pruning Continuous-depth Models [107.98191032466544]
  We show that pruning improves generalization for neural ODEs in generative modeling. We also show that pruning finds minimal and efficient neural ODE representations with up to 98% less parameters compared to the original network, without loss of accuracy.
  arXiv  Detail & Related papers  (2021-06-24T01:40:17Z)
• PolyDL: Polyhedral Optimizations for Creation of High Performance DL primitives [55.79741270235602]
  We present compiler algorithms to automatically generate high performance implementations of Deep Learning primitives. We develop novel data reuse analysis algorithms using the polyhedral model. We also show that such a hybrid compiler plus a minimal library-use approach results in state-of-the-art performance.
  arXiv  Detail & Related papers  (2020-06-02T06:44:09Z)
• Towards Real-Time DNN Inference on Mobile Platforms with Model Pruning and Compiler Optimization [56.3111706960878]
  High-end mobile platforms serve as primary computing devices for a wide range of Deep Neural Network (DNN) applications. constrained computation and storage resources on these devices pose significant challenges for real-time inference executions. We propose a set of hardware-friendly structured model pruning and compiler optimization techniques to accelerate DNN executions on mobile devices.
  arXiv  Detail & Related papers  (2020-04-22T03:18:23Z)
• Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
  Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters. Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques. We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
  arXiv  Detail & Related papers  (2020-02-03T04:11:13Z)
• PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning [57.20262984116752]
  We introduce a new dimension, fine-grained pruning patterns inside the coarse-grained structures, revealing a previously unknown point in design space. With the higher accuracy enabled by fine-grained pruning patterns, the unique insight is to use the compiler to re-gain and guarantee high hardware efficiency.
  arXiv  Detail & Related papers  (2020-01-01T04:52:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.