I am a Machine Learning researcher with interests in the security and robustness of machine learning algorithms, and applications in healthcare.
Currently, I am a Postdoctoral Research Associate at Modern Microprocessors Architecture Lab (MoMA Lab) in the Center for Cyber Security, New York University Abu Dhabi (NYUAD), where I work with Prof. Michail Maniatakos. My research focuses on attacking and defending algorithms in Federated Learning, with a particular emphasis on Backdoor Attacks, Machine Unlearning in both supervised and self-supervised learning.
If you are interested in collaborating, feel free to reach out.

Prior to joining NYUAD, I was a Senior Research Fellow (July 2022 - August 2024) at MBZUAI, where my research focused on developing training algorithms for energy-efficient Spiking Neural Networks (SNNs). My work emphasized direct supervised training and ANN-to-SNN conversion (i.e., transfer learning), in collaboration with Prof. Huan Xiong and Prof. Bin Gu.
Before MBZUAI, I was a Senior Research Scientist (July 2020 - June 2022) at the Big Data Lab of Baidu Research (Beijing), Baidu Inc.. During this period, I worked with Dr. Haoyi Xiong and Prof. Dejing Dou on model selection projects using machine learning methods and optimization.
I was also a visiting researcher in Industrial Engineering and Decision Analytics at HKUST from 2018 to 2019, hosted by Prof. Fugee TSUNG, where I worked on outlier detection in mobile phone data.

I obtained my Ph.D. in Statistics from School of Statistics and Data Science, Nankai University, under the supervision of Prof. Changliang Zou and Prof. Zhaojun Wang. My Ph.D. research focused on change-point detection of time-series data. I earned my M.S. in Probability and Statistics from Lanzhou University, supervised by Prof. Jianzhou Wang, and my B.S. in Mathematics from Lanzhou University.

My research interests lie broadly in machine learning security, privacy, and trustworthy AI, with a particular focus on developing resilient and privacy-preserving AI algorithms. I tackle these challenges from both applied and theoretical perspectives.

In Federated Learning Security, my research focuses on:

In Machine Unlearning & Data Privacy, I am particularly interested in:

My research aims to advance AI systems that are secure, privacy-preserving, and trustworthy, ensuring their safe deployment in real-world applications.