Skip to main content
Zhongkui Ma
PhD Student · Trustworthy AI Research

Hi, I'm Zhongkui Ma

Diving deep into my PhD journey atThe University of Queensland.

Formal MethodsNeural Network VerificationConvex Hull Approximation

News

Recent acceptances, awards, and publications

📄
Sept. 2026Paper Accepted

Our paper Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization is accepted by NeurIPS'26 as an oral presentation (112 of 30709 submissions, about 0.36%). Congrats, Zihan, Ethan and Zhongkui!

🏆
Aug. 2026Best Paper Award

Our paper Non-Transferable Examples receives the Best Paper Award - Runner Up at the ECCV'26 LifeGenIP Workshop. Congrats, Zihan!

📄
Mar. 2026Paper Accepted

Our paper Re-Key-Free, Risky-Free: Adaptable Model Usage Control is accepted by Euro S&P'26. Congrats, Zihan!

📄
Nov. 2025Paper Accepted

Our paper Mitigating Gradient Inversion Risks in Language Models via Token Obfuscation is accepted by Asia CCS'2026. Congrats, Xinguo!

📄
Aug. 2025Paper Accepted

Our paper Convex Hull Approximation for Activation Functions is accepted by OOPSLA'25 within SPLASH'25. Happy!

📄
Jan. 2025Paper Accepted

Our paper AI Model Modulation with Logits Redistribution is accepted by WWW'25. Congrats, Zihan!

📄
Aug. 2024Paper Accepted

Our paper Uncovering Gradient Inversion Risks in Practical Language Model Training is accepted by CCS'24. Congrats, Xinguo!

📄
Apr. 2024Paper Accepted

Our paper CORELOCKER: Neuron-level Usage Control is accepted by S&P'24. Congrats, Zihan! [Live Video]

📄
Nov. 2023Paper Accepted

Our paper ReLU Hull Approximation is accepted by POPL'24.

Guides & Tutorials

Comprehensive guides on neural network verification and recent blog posts

Recent Blogs

Featured NNV Guides

Open Source

Tools and libraries for neural network verification and ONNX workflows

Featured Verification Tools

WraLU

Verification Tool

Fast and precise ReLU hull approximation (POPL'24). Reported 10x-10^6x runtime improvements and up to 50% fewer constraints on the evaluated benchmarks.

WraAct

Verification Tool

Convex hull approximation for general activation functions (OOPSLA'25). Evaluated on Sigmoid, Tanh, MaxPool, and related cases with average 400x faster construction than SBLM+PDDM.

Supporting Libraries

wraact

Python Library

A unified Python library to approximate activation function hull with convex polytopes. Supports ReLU, LeakyReLU, ELU, Sigmoid, Tanh, and MaxPool.

View on GitHub

shapeonnx

ONNX Tool

A tool to infer missing tensor shapes in ONNX models for inspection and downstream tooling.

View on GitHub

slimonnx

ONNX Tool

A tool to optimize and simplify your ONNX models by removing redundant operations.

View on GitHub