Huan Zhang

2022 Early Career Fellow

Huan Zhang is an Assistant Professor at the University of Illinois Urbana-Champaign. He received his Ph.D. degree from UCLA in 2020. Huan’s research focuses on the trustworthiness of AI, especially on developing formal verification methods for deep neural networks. At UIUC, Huan’s team develops α,β-CROWN, a state-of-the-art neural network verifier that won the International Verification of Neural Networks Competition for five consecutive years (2021, 2022, 2023, 2024, 2025). α,β-CROWN has brought formal guarantees for learning-enabled systems in many fields and applications, such as robotics, control, and power systems.

AI2050 Project

The use of artificial intelligence (AI) is challenging in mission-critical scenarios such as aircraft control, autonomous driving, and medical procedures because AI is often an untrustable black-box. Through this fellowship, Huan’s research aims to improve and guarantee the trustworthiness of AI, making AI safer, more robust, more predictable and more reliable. Huan will focus on developing formal verification methods that can rigorously prove the trustworthiness of AI, enabling the use of AI in mission-critical systems with guaranteed performance.

Project artifacts

Z. Shi, Q. Jin, Z. Kolter, S. Jana, C. Hsieh, H. Zhang. Neural Network Verification with Branch-and-Bound for General Nonlinearities. arXiv. 2024.

L. Yang, H. Dai, Z. Shi, C. Hsieh, R. Tedrake, and H. Zhang. Lyapunov-stable neural control for state and output feedback: a novel formulation for efficient synthesis and verification. arXiv. 2024.

AI2050 Community Perspective — Huan Zhang (2024)

X. Guo, F. Yu, H. Zhang, L. Qin, and B. Hu. COLD-Attack: jailbreaking LLMs with stealthiness and controllability. arXiv. 2024.

S. Kotha, C. Brix, Z. Kolter, K. Dvijotham, and H. Zhang. Provably bounding neural network preimages. NeurIPS. 2023.

Affiliation

Assistant Professor, University of Illinois Urbana-Champaign

Hard Problem

Assurance