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, currently working on DNN Verification with Prof. ThanhVu Nguyen.

Research Interests

DNN Reasoning: Neural Network Verification and Testing, Formal Method, Proof Generation
Machine Learning: Reinforcement Learning

News

[Apr. 2025] CAV’25: research paper on the high-performance verification tool for DNNs.
[Jan. 2025] VNN-COMP’24: NeuralSAT ranked 2nd overall.
[Feb. 2024] FSE’24: research paper on optimizations for our DNN verification tool.
[Jan. 2024] VNN-COMP’23: NeuralSAT ranked 4th overall and received the New Participant Award (our first participation) and won the tllverifybench category.
[Dec. 2023] TACAS’24: research paper on a verifiable-friendly training method.

Publications

CAV'25

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

FSE'24

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

TACAS'24

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

ICSE-Demo'22

SymInfer: Inferring Numerical Invariants using Symbolic States (pp. 197–201)

ThanhVu Nguyen; KimHao Nguyen; Hai Duong

International Conference on Software Engineering (ICSE) - Companion Proceedings, 2022.

PDF Code

Misc

Proposal Contributions