monkbai/DNN-decompiler

BTD - Bin To DNN: A DNN Executables Decompiler

42
/ 100
Emerging

This project helps security researchers and reverse engineers understand how compiled Deep Neural Network (DNN) executables work on x86 CPUs. It takes a DNN executable as input and outputs a detailed model specification, including operator types, network topology, dimensions, and parameters. This is useful for analyzing proprietary models or understanding compiler optimizations, especially for those working with compiled AI/ML systems.

200 stars.

Use this if you need to reverse-engineer a compiled Deep Neural Network application running on x86 to understand its structure, operators, and parameters.

Not ideal if you are a data scientist primarily working with high-level AI/ML frameworks like TensorFlow or PyTorch and don't need to analyze compiled binaries.

reverse-engineering binary-analysis malware-analysis software-security deep-learning-compilers
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

200

Forks

5

Language

Python

License

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/monkbai/DNN-decompiler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.