Sijun Tan

I graduated with highest distinction from the University of Virginia with a Bachelor’s degree in Computer Science and Mathematics. During my undergraduate study, I worked with Professors David Wu and Yuan Tian on scalable privacy-preserving machine learning, and with Professors Haifeng Xu and Xiaohui Bei on handling miscalibration in peer reviews.

My research lies in cryptography, machine learning, and distributed systems. I am mainly interested in research in the following two directions: 1) build systems that can protect users’ data privacy by leveraging cryptographic tools. 2) studying cryptographic primitives that can improve the scalability, verifiability, and privacy of blockchain.


Sep 26, 2021 Our paper Least Square Calibration in Peer Reviews is accepted to appeear at NeurIPS2021.
Jul 14, 2021 I give a talk on my research work CryptGPU at Stanford Security Lunch.
Feb 19, 2021 Our paper CryptGPU: Fast Privacy Preserving Machine Learning on the GPU is accepted to appear at IEEE S&P2021.
May 19, 2020 I joined FAIR NY working on building and scaling CrypTen with GPU.

selected publications

  1. IEEE S&P
    CryptGPU: Fast Privacy Preserving Machine Learning on the GPU
    Sijun Tan, Brian Knott, Yuan Tian, and David Wu
    IEEE Symposium on Security and Privacy (S&P), 2021
  2. NeurIPS
    Least Square Calibration for Peer Reviews
    Sijun Tan, Jibang Wu, Xiaohui Bei, and Haifeng Xu
    Conference on Neural Information Processing Systems (NeurIPS) 2021