Xi He is a Canada CIFAR AI Chair at the Vector Institute. Her research focuses on the areas of privacy and security for big data, including the development of usable and trustworthy tools for data exploration and machine learning with provable security and privacy (S&P) guarantees.
Rather than patching systems for their S&P issues, her work takes a principled approach to designing provable S&P requirements and building practical tools that achieve these requirements. Considering S&P as a first-class citizen in system and algorithm design, she has demonstrated new optimization opportunities for these S&P-aware database systems and machine learning tools.
Xi He has published in the top database, privacy, and ML conferences including SIGMOD, VLDB, CCS, PoPets, AAAI, and presented highly regarded tutorials on privacy at VLDB 2016, SIGMOD 2017, and SIGMOD 2021. Her book “Differential Privacy for Databases,” co-authored by Joseph Near, was published in 2021.
- Meta Privacy-preserving Technologies Research Award, Meta, 2022
- Distinguished PC, ACM SIGMOD, 2021
- Outstanding Ph.D. Dissertation Award, Duke University, 2018
- Google PhD Fellowship in Privacy and Security, 2017
- Best Demo Award, International Conference on Very Large Data Bases, 2016
- Shubhankar Mohapatra, Sajin Sasy, Xi He, Gautam Kamath, Om Thakkar. The Role of Adaptive Optimizers for Honest Hyperparameter Tuning. AAAI Conference on Artificial Intelligence AAAI, 2022. Chang Ge, Shubhankar Mohapatra, Xi He, Ihab F. Ilyas. Kamino: Constraint-Aware Differentially Private Data Synthesis. International Conference on Very Large Data Bases VLDB, 2021.
- Near, J.P., He, X. (2021), "Differential Privacy for Databases", Foundations and Trends® in Databases, 8(2), p 109-225.
- Ios Kotsogiannis, Yuchao Tao, Xi He, Ashwin Machanavajjhala, Michael Hay, Gerome Miklau. PrivateSQL: A Differentially Private SQL Query Engine. International Conference on Very Large Data Bases VLDB, 2019.
- Xi He, Graham Cormode, Ashwin Machanavajjhala, Cecilia M. Procopiuc, Divesh Srivastava. DPT: Differentially Private Trajectory Synthesis using Hierarchical Reference Systems. International Conference on Very Large Data Bases VLDB, 2015.
- Xi He, Ashwin Machanavajjhala, Bolin Ding. Blowfish Privacy: Tuning Privacy-Utility Trade-offs using Policies. ACM Special Interest Group on Management of Data SIGMOD, 2014.
CIFAR is a registered charitable organization supported by the governments of Canada, Alberta and Quebec, as well as foundations, individuals, corporations and Canadian and international partner organizations.