Decompiling x86 Deep Neural Network Executables. (arXiv:2210.01075v2 [cs.CR] UPDATED)

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, …

decompiling network neural network x86