Paper 'General-Purpose f -DP Estimation and Auditing in a Black-Box Setting' accepted at USENIX 2025; paper 'Eureka: A General Framework for Black-box Differential Privacy Estimators' accepted at S&P 2024; published work 'The Normal Distributions Indistinguishability Spectrum and its Application to Privacy-Preserving Machine Learning' on arXiv; won the First Prize in the 2023 Korea National Cryptography Contest.
Research Experience
Worked as an AI Research Associate Intern at JPMorgan Chase, designing a new noise distribution mechanism; served as a visiting researcher at the University of Maryland (UMD).
Education
Currently a PhD student in Computer Science at Georgia Tech, supervised by Professor Vassilis Zikas. Previously pursued a PhD at Purdue University. Earned a Master's degree in Computer Science, a Bachelor's degree in Engineering, and a Bachelor's degree in Law from Nankai University in China.
Background
Research interests include machine learning, cryptography, and privacy. Focused on developing generic tools for differential privacy analysis to help people benefit from data while protecting privacy.
Miscellany
Collaborates with researchers in various fields, including secure computation, machine learning, symmetric key cryptography, and game theory.