Scholar
Bochuan Cao
Google Scholar ID: eOZCg2IAAAAJ
The Pennsylvania State University, PhD student
Citations & Impact
Citations
576
H-index
10
i10-index
10
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- - Published multiple papers in top conferences like NeurIPS and ACL, including 'Data Free Backdoor Attacks' and 'Personalized Steering of Large Language Models'.
- - Involved in research projects covering trustworthiness, security, and privacy protection of large language models.
- - Some research results have released code, such as 'Defending Against Alignment-Breaking Attacks via Robustly Aligned LLM'.
Research Experience
- - Served as the main author or co-author in multiple research projects, involving various aspects such as the security of large language models, privacy protection, and adversarial attacks.
Education
- - Pennsylvania State University, Ph.D. candidate (expected to graduate in 2026), Advisor: Dr. Jinghui Chen
- - University of Electronic Science and Technology of China (UESTC), Bachelor's degree, 2022
Background
- - Research interests include trustworthiness and security issues in large language models, safety and privacy issues in image generation models, and interpretation and evaluation of large pre-trained models.
- - Currently a Ph.D. candidate at Pennsylvania State University, advised by Dr. Jinghui Chen.
Miscellany
- - Actively seeking full-time research positions and faculty opportunities for 2026.
- - Welcomes discussions on research works.
