Scholar
Zihao Zhu
Google Scholar ID: PnLq3EwAAAAJ
The Chinese University of Hong Kong, Shenzhen
Citations & Impact
Citations
750
H-index
13
i10-index
14
Publications
20
Co-authors
14
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models' and 'To Think or Not to Think: Exploring the Unthinking Vulnerability in Large Reasoning Models'. Additionally, an open-source project 'Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers' has been accepted to NeurISP 2025 workshop.
Research Experience
- Involved in multiple research projects related to AI security, including robust safety alignment of large reasoning models, defenses and attacks in adversarial machine learning.
Education
- Currently a Ph.D. student in Data Science at The Chinese University of Hong Kong, Shenzhen, under the supervision of Prof. Baoyuan Wu; received Master’s degree from the Institute of Information Engineering at the University of Chinese Academy of Sciences in 2021.
Background
- Research interests include: safety of large language models, data safety in AI systems, and safety in embodied AI. Currently on the job market and seeking full-time opportunities in academia or industry.
Miscellany
- On the job market and seeking full-time opportunities in academia or industry.
