Hi, I'm Zhongkui Ma
Diving deep into my PhD journey at The University of Queensland.
News
Latest updates and announcements
Our paper Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation is accepted by AsiaCCS'2026. Congrats, Xinguo!
I present our work Convex Hull Approximation for Activation Functions at OOPSLA'25 in Singapore (Thu 16 Oct 2025 16:00-16:15 at Orchid West of Marina Bay Sands Convention Centre).
Our paper Convex Hull Approximation for Activation Functions is accepted by OOPSLA'25 within SPLASH'25. Happy!
Our paper AI Model Modulation with Logits Redistribution is accepted by WWW'25. Congrats, Zihan!
Prof. Bai and I have a tutorial on Robustness Verification of Neural Networks using WraLU at ADC'24 (Tue 16 Dec 2024, Gold Coast, Australia). We are awarded the Distinguished Tutorial Speaker!
Guides & Tutorials
Comprehensive guides on neural network verification and recent blog posts
Recent Blogs
PropDAG
A template framework for bound propagation
ShapeONNX
Solving ONNX's dynamic shape problem
SlimONNX
ONNX optimization for verification workflows
Featured NNV Guides
Neural Network Verification
Learn neural network verification in 3 minutes: core concepts and quick overview
Verification Problem
Mathematical formulation of neural network verification and certification
Bound Propagation
Core verification method using Interval Bound Propagation (IBP) and abstract interpretation
Open Source
Tools and libraries for neural network verification
Featured Verification Tools
Supporting Libraries
wraact
Python LibraryA unified Python library to approximate activation function hull with convex polytopes. Supports ReLU, Sigmoid, Tanh, and GeLU.
View on GitHubshapeonnx
ONNX ToolA tool to infer the shape of an ONNX model when the official tool is down.
View on GitHubslimonnx
ONNX ToolA tool to optimize and simplify your ONNX models by removing redundant operations.
View on GitHub