Lei Yu is a Tenure-Track Assistant Professor in the Department of Computer Science at Rensselaer Polytechnic Institute. Before that, he was a Research Staff Member at IBM Research, IBM Thomas J. Watson Research Center. His research interests include data privacy and security, trustworthy AI, machine learning systems, and cloud & mobile computing.

About Me

My recent research interests focus on data privacy, AI security and machine learning techniques for system security. My research on data privacy targets at identifying privacy threats and risks during different phases of data life-cycle and the issues of existing privacy protection designs, and developing principled privacy-preserving algorithmic and systematic solutions. The goal is to effectively protect data privacy and ensure regulatory compliance while preserving data utility.

I earned my Ph.D. in Computer Science from Georgia Institute of Technology, focusing on research in big data privacy and deep learning privacy. After that, I joined IBM Research, where my work has spanned large-scale log based system anomaly detection, AI-Ops, system data privacy identification and protection, and machine learning system optimization. Additionaly, I hold a Ph.D. degree from Harbin Institute of Technology, China. My earlier research involved wireless sensor network, cloud computing, and algorithmic solutions for improving the performance of distributed systems.

Recent News ()

  • , Our paper “Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control” has been accepted by IJCAI 2024 [PDF] [Code].
  • , Our in-depth survey on privacy in Vertical Federated Learning is now available on arXiv. If you’re interested in VFL privacy research, please check it out [PDF].
  • , A preprint on LLM for backdoor attacks is now available on arXiv. [PDF] [Code].
  • , Invited to serve as PC member (for Track of Security, Privacy, and Trust in Distributed Systems) for IEEE ICDCS’24.
  • , We have been awarded AIRC RPI-IBM research grant.
  • , Our paper “A Comparison of End-to-End Decision Forest Inference Pipelines” has been accepted to ACM SoCC 2023. Thanks to all the co-authors.
  • , Our paper “Privacy-Preserving Redaction of Diagnosis Data through Source Code Analysis” has been accepted to SSDBM 2023. Many thanks to Lixi, Prof. Jia Zou and Hong Min!