Xun Wang - Ph.D. Student at CISPA

About Me

I am currently a second-year Ph.D. student at CISPA Helmholtz Center for Information Security, where I conduct cutting-edge research at the intersection of machine learning and security. I am co-supervised by Prof. Michael Backes, Prof. Franziska Boenisch, and Prof. Adam Dziedzic at SprintML Lab.

Prior to my doctoral studies, I obtained my M.S. degree in Computer Science from Technical University of Munich (TUM) in 2023, graduating with high distinction. I completed my B.S. degree at Tongji University in 2020.

Research Interests

My research focuses on developing efficient and privacy-preserving machine learning systems. I am particularly interested in:

• Neural Network Pruning & Compression: Developing structured pruning techniques that maintain model performance while reducing computational overhead
• Privacy-Preserving ML: Creating methods for secure and private transfer learning, particularly in the context of large language models
• Efficient Deep Learning: Designing algorithms that make deep learning more accessible and practical for resource-constrained environments
• Machine Learning Security: Investigating vulnerabilities and defenses in ML systems

Current Research Highlights

• Structurally Prune Anything (SPA): A versatile framework for structured pruning that works across any architecture, framework, and training stage
• Privacy-Preserving Soft Prompt Transfer (POST): Efficient methods for transferring knowledge in LLMs while preserving privacy