Skip to content
View ZhongkuiMa's full-sized avatar
😁
Keep working
😁
Keep working

Highlights

  • Pro

Block or report ZhongkuiMa

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ZhongkuiMa/README.md

Hey there! I'm Zhongkui Ma (马中奎)~ 👋

I’m a PhD student at the University of Queensland 🎓, deeply immersed in the fascinating world of neural networks 🤖—a constantly evolving field that pushes me to think outside the box every single day!

My research focuses on neural network verification (NNV) 🧠💪. I’m passionate about ensuring these powerful models are robust, reliable, and dependable, regardless of the conditions or inputs they encounter.

Want to know more about me? Visit my website: zhongkuima.github.io


Published Projects 📚

I’ve worked on several exciting projects related to neural networks and model security, some of which have been published in top-tier conferences:


Latest Projects 🔧

I’m currently working on some exciting tools that I’m thrilled to share with you:

  • slimonnx: A tool to optimize and simplify your ONNX models by removing redundant operations and resolving version issues. It makes ONNX files cleaner, more efficient, and ready for action! 🚀 (Currently in development 🛠️)
  • torchonnx: A tool for converting ONNX models to PyTorch models (.pth for parameters, .py for structure). It’s simple, lightweight, and designed for seamless model conversion 🔄. (Currently in development 🛠️)
  • torchvnnlib: A tool to convert VNN-LIB files (.vnnlib) to PyTorch tensors (.pth files) for efficient neural network verification. Take full advantage of the PyTorch ecosystem! 🚀
  • propdag: A bound propagation framework for neural network verification. It supports any DAG (Directed Acyclic Graph) structure, covering both feedforward and backward propagation patterns for verification. This tool allows researchers to focus on their algorithms without worrying about complex computation graphs! 💪

Thanks so much for visiting my GitHub! Let’s innovate, collaborate, and make AI even better together! ⭐

Pinned Loading

  1. UQ-Trust-Lab/WraLU UQ-Trust-Lab/WraLU Public

    An algorithm to calculate the convex hull of ReLU function for neural network verification.

    Python 3 1

  2. UQ-Trust-Lab/PdD UQ-Trust-Lab/PdD Public

    A Character-level Perturbation Generator based on probability distribution, density and diversity.

    Python 2

  3. slimonnx slimonnx Public

    slimonnx is a tool to simplify or optimize an ONNX model (.onnx file).

    Python 2

  4. torchonnx torchonnx Public

    torchonnx is a tool to convert an ONNX model (.onnx file) to a pytorch model (.pth file for model parameters and .py file for neural network structure).

    Python 2

  5. torchvnnlib torchvnnlib Public

    torchvnnlib is a tool to convert .vnnlib file into .pth file with tourch tensors.

    Python 1

  6. propdag propdag Public

    propdag is a framework to develop bound propagation approaches for neural network verification.

    Python 1