About Me
I am a PhD student in Cybersecurity at George Mason University, with a Master’s degree from the University of Chinese Academy of Sciences. My research focuses on the security and privacy of large language models (LLMs), with a particular interest in LLM unlearning techniques. I am a member of the SPARK Lab, led by Prof. Zhuangdi Zhu, where we explore cutting-edge solutions to enhance privacy and security in AI-driven technologies.
- Artificial Intelligence
- Large Language Model
- Machine Unlearning
- Security & Privacy
PhD Cybersecurity
George Mason University
MEng CyberSecurity
University of Chinese Academy of Sciences
BSc Computer Science
Harbin University of Science and Technology
During my PhD, I focus on the security of large language models, specifically researching efficient methods for unlearning. This not only makes the models more practical for real-world use but also addresses privacy, copyright, and ethical concerns.
During my master’s period, I explored the intersection of machine learning and information security, drawing on my undergraduate research background in this area. I worked on employing robust learning methods to defend against poisoning attacks in federated learning while utilizing cryptographic techniques to protect privacy.
Please reach out to collaborate 😃