Decompiling x86 Deep Neural Network Executables

• URL: http://arxiv.org/abs/2210.01075v2
• Date: Tue, 4 Oct 2022 11:45:23 GMT
• Title: Decompiling x86 Deep Neural Network Executables
• Authors: Zhibo Liu, Yuanyuan Yuan, Shuai Wang, Xiaofei Xie, Lei Ma
• Abstract summary: 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.
• Score: 20.91585339813852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Due to their widespread use on heterogeneous hardware devices, deep learning (DL) models are compiled into executables by DL compilers to fully leverage low-level hardware primitives. This approach allows DL computations to be undertaken at low cost across a variety of computing platforms, including CPUs, GPUs, and various hardware accelerators. We present BTD (Bin to DNN), a decompiler for deep neural network (DNN) executables. BTD takes DNN executables and outputs full model specifications, including types of DNN operators, network topology, dimensions, and parameters that are (nearly) identical to those of the input models. BTD delivers a practical framework to process DNN executables compiled by different DL compilers and with full optimizations enabled on x86 platforms. It employs learning-based techniques to infer DNN operators, dynamic analysis to reveal network architectures, and symbolic execution to facilitate inferring dimensions and parameters of DNN operators. Our evaluation reveals that BTD enables accurate recovery of full specifications of complex DNNs with millions of parameters (e.g., ResNet). The recovered DNN specifications can be re-compiled into a new DNN executable exhibiting identical behavior to the input executable. We show that BTD can boost two representative attacks, adversarial example generation and knowledge stealing, against DNN executables. We also demonstrate cross-architecture legacy code reuse using BTD, and envision BTD being used for other critical downstream tasks like DNN security hardening and patching.

Related papers

• SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget [18.63754969602021]
  Deep neural networks (DNNs) on edge artificial intelligence (AI) devices enable various autonomous mobile computing applications. Existing solutions, such as model compression or cloud offloading, reduce the memory footprint of DNN inference. We develop SwapNet, an efficient block swapping ecosystem for edge AI devices.
  arXiv  Detail & Related papers  (2024-01-30T05:29:49Z)
• 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)
• Sparsifying Binary Networks [3.8350038566047426]
  Binary neural networks (BNNs) have demonstrated their ability to solve complex tasks with comparable accuracy as full-precision deep neural networks (DNNs) Despite the recent improvements, they suffer from a fixed and limited compression factor that may result insufficient for certain devices with very limited resources. We propose sparse binary neural networks (SBNNs), a novel model and training scheme which introduces sparsity in BNNs and a new quantization function for binarizing the network's weights.
  arXiv  Detail & Related papers  (2022-07-11T15:54:41Z)
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks [72.81092567651395]
  Sub-bit Neural Networks (SNNs) are a new type of binary quantization design tailored to compress and accelerate BNNs. SNNs are trained with a kernel-aware optimization framework, which exploits binary quantization in the fine-grained convolutional kernel space. Experiments on visual recognition benchmarks and the hardware deployment on FPGA validate the great potentials of SNNs.
  arXiv  Detail & Related papers  (2021-10-18T11:30:29Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• ShiftAddNet: A Hardware-Inspired Deep Network [87.18216601210763]
  ShiftAddNet is an energy-efficient multiplication-less deep neural network. It leads to both energy-efficient inference and training, without compromising expressive capacity. ShiftAddNet aggressively reduces over 80% hardware-quantified energy cost of DNNs training and inference, while offering comparable or better accuracies.
  arXiv  Detail & Related papers  (2020-10-24T05:09:14Z)
• 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)
• 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.