Hi! My name is Yunzhuo Hao (郝韵焯), a third-year undergraduate in School of Information and Software Engineering at the University of Electronic Science and Technology of China (UESTC). I’m a research intern at Gaoling School of Artificial Intelligence, Renmin University of China, where I’m fortunate to work with Prof. Yankai Lin. My research interests mainly lie in Machine Learning (ML) and Natural Language Processing (NLP), specifically including the trustworthiness and security issues in large language models and also federated machine learning security problems. I am also interested in other issues related to LLMs, such as LLM alignment, etc.

Education

• Sept. 2021 - July 2025 (expected), Bachelor in School of Information and Software Engineering (SISE), University of Electronic Science and Technology of China (UESTC).

Internship

• Oct. 2023 - Present, Research Assistant, Gaoling School of Artificial Intelligence, Renmin University of China, working on the security of Large Language Models (LLMs), supervised by Prof. Yankai Lin.

Preprints

(# denotes Equal Contribution)

• Exploring Backdoor Attacks on Chat Models
  Yunzhuo Hao#, Wenkai Yang#, Yankai Lin
  [arxiv, code]

Honors and Awards

• Oct. 2023 2022-2023 China National Scholarship (top 1%)
• Oct. 2023 2022-2023 Outstanding students of UESTC
• Oct. 2022 2021-2022 China National Scholarship (top 1%)
• Oct. 2022 2021-2022 Outstanding students of UESTC