purseclab/DnD
A decompiler to automatically reverse-engineer the DNN semantics from its compiled binary using program analysis
When you have a compiled deep neural network (DNN) model and need to understand its structure and how it was designed, this tool helps by reverse-engineering the model. It takes the compiled binary of a DNN as input and outputs a standardized ONNX file, which is a common format for representing machine learning models. This is useful for security researchers, embedded systems developers, or anyone needing to inspect or re-use existing DNN implementations where the original model code is unavailable.
No commits in the last 6 months.
Use this if you need to recover the architecture and parameters of a deep neural network from its compiled binary, especially for security analysis or re-purposing models.
Not ideal if you already have access to the original source code or model definition files (like Keras, TensorFlow, or PyTorch models).
Stars
83
Forks
11
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 17, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/purseclab/DnD"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
keras-team/keras
Deep Learning for humans
Lightning-AI/torchmetrics
Machine learning metrics for distributed, scalable PyTorch applications.
Lightning-AI/pytorch-lightning
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
lanpa/tensorboardX
tensorboard for pytorch (and chainer, mxnet, numpy, ...)