Publications

PII-VisBench: Evaluating Personally Identifiable Information Safety in Vision Language Models Along a Continuum of Visibility

G M Shahariar, Zabir Al Nazi, Md Olid Hasan Bhuiyan, Zhouxing Shi

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits

Yizhak Yisrael Elboher*, Avraham Raviv*, Amihay Elboher*, Zhouxing Shi, Omri Azencot, Hillel Kugler, Guy Katz

PIKA: Expert-Level Synthetic Datasets for Post-Training Alignment from Scratch

Code

Shangjian Yin, Shining Liang, Wenbiao Ding, Yuli Qian, Zhouxing Shi, Hongzhi Li, Yutao Xie

Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control

Code

Zhouxing Shi, Haoyu Li, Cho-Jui Hsieh, Huan Zhang

NeurIPS 2025 Workshop on Constrained Optimization for Machine Learning

SoundnessBench: A Soundness Benchmark for Neural Network Verifiers

Code

Benchmark

arXiv

Xingjian Zhou*, Keyi Shen*, Andy Xu*, Hongji Xu*, Cho-Jui Hsieh, Huan Zhang, Zhouxing Shi

TMLR 2025

Trustworthy AI with Verifiable Guarantees and Empirical Robustness

Zhouxing Shi

PhD Dissertation

Neural Network Verification with Branch-and-Bound for General Nonlinearities

Code

Benchmark

arXiv

Zhouxing Shi*, Qirui Jin*, Zico Kolter, Suman Jana, Cho-Jui Hsieh, Huan Zhang

TACAS 2025

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation

Code

Benchmark

Press

arXiv

Lujie Yang*, Hongkai Dai*, Zhouxing Shi, Cho-Jui Hsieh, Russ Tedrake, Huan Zhang

ICML 2024

Defending LLMs against Jailbreaking Attacks via Backtranslation

Code

arXiv

Yihan Wang*, Zhouxing Shi*, Andrew Bai, Cho-Jui Hsieh

ACL-Findings 2024

Red Teaming Language Model Detectors with Language Models

Code

arXiv

Zhouxing Shi*, Yihan Wang*, Fan Yin*, Xiangning Chen, Kai-Wei Chang, Cho-Jui Hsieh (*Alphabetical)

TACL 2024 (presented at EMNLP 2024)

Formal Verification for Neural Networks with General Nonlinearities via Branch-and-Bound

Zhouxing Shi*, Qirui Jin, Huan Zhang, Zico Kolter, Suman Jana, Cho-Jui Hsieh

WFVML 2023 (ICML workshop)

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data

Demo

arXiv

Zhouxing Shi, Nicholas Carlini, Ananth Balashankar, Ludwig Schmidt, Cho-Jui Hsieh, Alex Beutel, Yao Qin

NeurIPS 2023

Towards Robustness Certification Against Universal Perturbations

Code

Yi Zeng*, Zhouxing Shi*, Ming Jin, Feiyang Kang, Lingjuan Lyu, Cho-Jui Hsieh, Ruoxi Jia

ICLR 2023

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Code

arXiv

Zhouxing Shi, Yihan Wang, Huan Zhang, Zico Kolter, Cho-Jui Hsieh

NeurIPS 2022

On the Adversarial Robustness of Vision Transformers

Code

arXiv

Rulin Shao, Zhouxing Shi, Jinfeng Yi, Pin-Yu Chen, Cho-Jui Hsieh

TMLR 2022

On the Sensitivity and Stability of Model Interpretations in NLP

arXiv

Fan Yin, Zhouxing Shi, Cho-Jui Hsieh, Kai-Wei Chang

ACL 2022

On the Convergence of Certified Robust Training with Interval Bound Propagation

arXiv

Yihan Wang*, Zhouxing Shi*, Quanquan Gu, Cho-Jui Hsieh

ICLR 2022

Robust Text CAPTCHAs Using Adversarial Examples

arXiv

Rulin Shao, Zhouxing Shi, Jinfeng Yi, Pin-Yu Chen, Cho-Jui Hsieh

BigData 2022

Fast Certified Robust Training with Short Warmup

Code

arXiv

Zhouxing Shi*, Yihan Wang*, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh

NeurIPS 2021

Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond

Code

arXiv

Kaidi Xu*, Zhouxing Shi*, Huan Zhang*, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh

NeurIPS 2020

Robustness Verification for Transformers

Code

arXiv

Zhouxing Shi, Huan Zhang, Kai-Wei Chang, Minlie Huang, Cho-Jui Hsieh

ICLR 2020

Robustness to Modification with Shared Words in Paraphrase Identification

Code

arXiv

Zhouxing Shi, Minlie Huang

EMNLP-Findings 2020

A Deep Sequential Model for Discourse Parsing on Multi-Party Dialogues

Code

arXiv

Zhouxing Shi, Minlie Huang

AAAI 2019

Preprints (* Equal contribution)

Publications (* Equal contribution)