Hai Duong

Ph.D. Student
George Mason University
hduong22 (at) gmu.edu

About Me

I am a Ph.D. student in Computer Science at George Mason University, working with Prof. ThanhVu Nguyen at ROARS Lab on Deep Neural Network Verification.

Research Interests

DNN Verification and Testing
Formal Method, Automated Reasoning
Proof Generation and Checking

News

04/2025: CAV’25 paper on the NeuralSAT DNN verification tool .
07/2024: NeuralSAT ranked 2nd overall in VNN-COMP’24. GMU Press.
02/2024: FSE’24 paper on new optimizations developed for the NeuralSAT.
12/2023: TACAS’24 paper on a verifiable-friendly training method.
07/2023: NeuralSAT ranked 4th overall and received New Participant Award in VNN-COMP’23.

Publications

1. NeuralSAT: A High-Performance Verification Tool for Deep Neural Networks (to appear)

Hai Duong; ThanhVu Nguyen; Matthew B. Dwyer

Computer Aided Verification (CAV), 2025.

PDF Code
2. Harnessing Neuron Stability to Improve DNN Verification (pp. 859-881)

Hai Duong; Dong Xu; ThanhVu Nguyen; Matthew B. Dwyer

Foundations of Software Engineering (FSE), 2024.

PDF Code
3. Training for Verification: Increasing Neuron Stability to Scale DNN Verification (pp. 24-44)

Dong Xu; Nusrat Jahan Mozumder; Hai Duong; Matthew B. Dwyer

Tools and Algorithms for the Construction and Analysis of Systems (TACAS), 2024.

PDF Code

Misc

Contribute to proposal NSF CAREER. NeuralSAT: A Constraint-Solving Framework for Verifying Deep Neural Networks. 2023.
Contribute to proposal Amazon Research Award. Scalable and Precise DNN Constraint Solving with Abstraction and Conflict Clause Learning. 2022.
Help review papers at ISSTA 2023, OOPSLA 2024, PLDI 2024