Muchao Ye

Assistant Professor, University of Iowa

Joined

November 2021

Names

Muchao Ye (Preferred)

Emails

****@psu.edu (Confirmed)

****@gmail.com (Confirmed)

****@uiowa.edu (Confirmed)

Personal Links

Career & Education History

Assistant Professor

University of Iowa (uiowa.edu)

2024 – Present

PhD student

Pennsylvania State University (psu.edu)

2020 – 2024

Advisors, Relations & Conflicts

PhD Advisor

Fenglong Ma

2020 – Present

Expertise

Vision Language Models

2024 – Present

Adversarial Machine Learning

2020 – Present

Sequential Modeling

2018 – Present

Machine Learning

2018 – Present

Publications

Polar: Automating Cyber Threat Prioritization through LLM-Powered Assessment
Luoxi Tang, Yuqiao Meng, Ankita Patra, Weicheng Ma, Muchao Ye, Zhaohan Xi
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Two are Better than One: Uncertainty-Aware Vision-Language Models for Video Anomaly Detection
Muchao Ye, Haomiao Ni, Xianren Zhang, Weiyang Liu, Pan He
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
It is Hard to Unlearn Dogged Backdoor Samples in Diffusion Models
An Huang, Zuobin Xiong, Muchao Ye, Junggab Son
- NeurIPS 2025 - Reliable ML Workshop
- Readers: Everyone
VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models
Pan He, Muchao Ye, Weiyang Liu
- OpenReview Archive Direct Upload
- Readers: Everyone
Robustifying Safety-Aligned Large Language Models through Clean Data Curation
Xiaoqun Liu, Jiacheng Liang, Muchao Ye, Zhaohan Xi
- Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI)
- Readers: Everyone
Buckle Up: Robustifying LLMs at Every Customization Stage via Data Curation
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang, Chenyu You, Muchao Ye, Zhaohan Xi
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
Ziyi Yin, Muchao Ye, Tianrong Zhang, Tianyu Du, Jinguo Zhu, Han Liu, Jinghui Chen, Ting Wang, Fenglong Ma
- NeurIPS 2023 poster
- Readers: Everyone
UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation
Muchao Ye, Ziyi Yin, Tianrong Zhang, Tianyu Du, Jinghui Chen, Ting Wang, Fenglong Ma
- NeurIPS 2023 poster
- Readers: Everyone
Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation
Xingyi Yang, Muchao Ye, Quanzeng You, Fenglong Ma
- 31 Mar 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
LeapAttack: Hard-Label Adversarial Attack on Text via Gradient-Based Optimization
Muchao Ye, Jinghui Chen, Chenglin Miao, Ting Wang, Fenglong Ma
- 2022 (modified: 09 Nov 2022)
- KDD 2022
- Readers: Everyone

View all 22 publications

Co-Authors

View all 38 co-authors