News

News#

New!!! 🎉 🎉 🎉

[Jan. 2025] Our paper AI Model Modulation with Logits Redistribution is accepted by the ACM Web Conference 2025 (WWW’25). Congrats, Zihan!
[Dec. 2024] Prof. Bai and I have a tutorial on Robustness Verification of Neural Networks using WraLU in the Australasian Database Conference (ADC’24) on Tue 16 Dec 2024 16:30 AEST (UTC+10) in Gold Coast, Australia. We are awarded the Distinguished Tutorial Speaker!
[Dec. 2024] I will serve the ACM SIGPLAN International Conference on Systems, Programming, Languages and Applications: Software for Humanity (SPLASH’25) as a member committee member in artifact evaluation committee within the SPLASH OOPSLA Artifacts-track.
[Aug. 2024] Our paper Uncovering Gradient Inversion Risks in Practical Language Model Training is accepted by the 31th ACM Conference on Computer and Communications Security (CCS’24). Congrats, Xinguo!
[May. 2024] I will have a presentation about ReLU Hull Approximation in the workshop Formal Methods in Australia and New Zealand during 29–30 May 2024 at the University of Queensland, St Lucia. My presentation time is 15:30–16:00 on 30 May 2024.
[Apr. 2024] I will present our work ReLU Hull Approximation in FPench community monthly meeting on May 2nd at 9:00-10:00 AM Pacific time.
[Apr. 2024] Our paper CORELOCKER: Neuron-level Usage Control is accepted by the 45th IEEE Symposium on Security and Privacy (S&P’24). Congrats, Zihan! [Live Video]
[Jan. 2024] I present our work, ReLU Hull Approximation in POPL’24 in Kelvin Room of the Institution of Engineering and Technology (IET) at London, UK. [Live Video]
[Jan. 2024] I will serve the 45th ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI’24) as a committee member in artifact evaluation committee within the research artifacts-track.
[Nov. 2023] Our paper ReLU Hull Approximation is accepted by the 51st ACM SIGPLAN Symposium on Principles of Programming Languages (POPL’24).
[Nov. 2023] I participate in the 24th International Conference on Formal Engineering Methods (ICFEM’23) at Brisbane, Australia. And I present our work, Formalizing Robustness Against Character-Level Perturbations for Neural Network Language Models and my doctoral symposium paper, Verifying Neural Networks by Approximating Convex Hulls..

Recent Small Interests#

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

shapeonnx: A tool to infer the shape of an ONNX model when the official tool is down. It’s a simple yet powerful tool that helps you understand the dimensions of your model’s inputs and outputs!
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!
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.
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.

The above map shows the distribution of visitors to this website.
This widget is provided by ClustrMaps.

Contents: