About me

Hello! I’m Yuxuan Zhu, a second-year PhD student in Computer Science at Rensselaer Polytechnic Institute (RPI). I received a bachelor’s degree in Electrical Engineering (Medical Informatics track) from Sichuan University in China, and a master’s degree in Computer Science from Leiden University in the Netherlands.

Research Interests

My research focuses on the intersection of efficiency and robustness in machine learning models, with a particular emphasis on Large Language Models (LLMs) and Graph Neural Networks (GNNs). I also have experience in Explainable AI (XAI) and anomaly detection.

• LLM: Investigating challenges related to improving the efficiency of LLMs, with a special focus on KV cache compression.
• GNN: Exploring the robustness, security, and interpretability of GNNs, particularly in the context of backdoor attacks and defense mechanisms.

I am driven by a deep curiosity and a commitment to advancing AI to solve complex, real-world problems.

News

• [08/2024] Our paper titled On the Robustness of Graph Reduction Against GNN Backdoor was accepted by AISec’24 CCS 2024 (acceptance rate: 25%) for publication!
  
• [09/2023] Moved from 🇳🇱 to 🇺🇸. Started my PhD journey at RPI!
  
• [07/2023] Our paper titled A Survey on Explainable Anomaly Detection was accepted by TKDD for publication!
  
• [03/2023] Graduated from Leiden University in the Netherlands with a master’s degree in Computer Science [thesis].
  
• [02/2023] Completed my graduation thesis/internship Data-driven Nozzle Failures Detection and Classification at Canon Production Printing.

Services

• Reviewer, Conference on Neural Information Processing Systems (NeurIPS), 2024
  
• Reviewer, International Conference on Distributed Computing Systems (ICDCS), 2024
  
• Reviewer, The International Conference on Learning Representations (ICLR), 2025