Zaitang Li, Ph.D. Candidate
Computer Science and Engineering
The Chinese University of Hong Kong
About Me
I am a Ph.D. candidate in Computer Science and Engineering at The Chinese University of Hong Kong (CUHK). I am advised by Prof. Tsung-Yi Ho and co-supervised by Dr. Pin-Yu Chen from IBM. My research focuses on trustworthiness in Large Language Models (LLMs), including robustness evaluation, jailbreak risk quantification, and adversarial perturbation analysis.
Research Interests
- Trustworthy AI
- Robustness Evaluation of LLMs
- Adversarial Machine Learning
- Knowledge Graphs and Text Generation
News
- [2024-09] Our paper “GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models” was accepted at NeurIPS 2024!
- [2024-12] Our paper “Retention Score: Quantifying Jailbreak Risks for Vision Language Models” was accepted at AAAI 2025!
Publications
Conference Proceedings
- Z. Li, P.-Y. Chen, and T.-Y. Ho, “Retention Score: Quantifying Jailbreak Risks for Vision Language Models,” in AAAI 2025.
- Z. Li, P.-Y. Chen, and T.-Y. Ho, “GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models,” in NeurIPS 2024.
Education
- Ph.D. in Computer Science and Engineering (Expected 2026)
The Chinese University of Hong Kong (CUHK) - B.Sc. in Math and Information Engineering (2022)
The Chinese University of Hong Kong (CUHK), First Honor, Minor: Statistics
Contact
- Email: 1155107739@link.cuhk.edu.hk
- Google Scholar: Zaitang Li
- GitHub: lizaitang
- Personal Website: https://lizaitang.github.io