I am a Computing Innovation Fellow at Harvard John A. Paulson School Of Engineering And Applied Sciences, hosted by Salil Vadhan. I received my Ph.D. from the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech, where I was advised by Rachel Cummings and Yajun Mei. Prior to Georgia Tech, I received my B.S. in Statistics at Peking University. In Summer 2019, I interned at Microsoft Research Cambridge, working with Olya Ohrimenko and Shruti Tople. In summer 2020, I worked with Nalin Singal , Robert Sim, Jana Kulkarni and Priyanka Kulkarni at Microsoft Research AI.

My research has been focused on data privacy, in particular, in differential privacy, including (1) developing the theoretical foundations, (2) designing privacy-preserving algorithms for machine learning models and statistical analysis tools, and (3) adapting existing tools to solve domain-specific questions. In addition, I am interested in (4) broader privacy concerns, including understanding privacy vulnerabilities and proposing solutions. Currently, I’m broadly interested in responsible AI.


Conference Papers

Note: The convention in TCS is to list authors in alphabetical order. (* indicates primary author)

Membership Inference Attacks and Privacy in Topic Modeling
Nico Manzonelli, Wanrong Zhang, Salil Vadhan
In submission. 2023.

Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training
Alyssa Huang, Peihan Liu, Ryumei Nakada, Linjun Zhang, Wanrong Zhang
In submission. 2023.

Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters
Samuel Haney, Michael Shoemate, Grace Tian, Salil Vadhan, Andrew Vyrros, Vicki Xu*, Wanrong Zhang* (Alphabetical order)
CCS . 2023. [paper]
CCS 2023 Distinguished Paper Award

Continual Release of Differentially Private Synthetic Data
Mark Bun, Marco Gaboardi, Marcel Neuhoeffer, Wanrong Zhang (Alphabetical order)
PODS . 2024. [paper]

DP-Fast MH: Private, Fast, and Accurate Metropolis-Hastings for Large-Scale Bayesian Inference
Wanrong Zhang, Ruqi Zhang
ICML . 2023. [paper]

Concurrent Composition Theorems for Differential Privacy
Salil Vadhan, Wanrong Zhang* (Alphabetical order)
STOC . 2023. [paper]
Poster presentation in TPDP @ICML. 2022.

Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size
Wanrong Zhang, Yajun Mei, Rachel Cummings
AISTATS. 2022. [paper]
Poster presentation in TPDP @ICML. 2021.

Attribute Privacy: Framework and Mechanisms
Wanrong Zhang, Olga Ohrimenko, Rachel Cummings
ACM FAccT. 2022. [paper]
Presentation at FORC. 2021, non-archival track.
Poster presentation in TPDP @CCS. 2020.

Leakage of Dataset Properties in Multi-Party Machine Learning
Wanrong Zhang, Shruti Tople, Olga Ohrimenko
USENIX Security Symposium. 2021. [paper]

PAPRIKA: Private Online False Discovery Rate Control
Wanrong Zhang, Gautam Kamath, Rachel Cummings
ICML. 2021. [paper][code]
Presentation at FORC. 2021, non-archival track.
Poster presentation in TPDP @CCS. 2020.

Privately Detecting Changes in Unknown Distributions
Rachel Cummings, Sara Krehbiel, Yuliia Lut, Wanrong Zhang* (Alphabetical order)
ICML. 2020. [paper]
Poster presentation in TPDP @CCS. 2019.

Differentially Private Change-point Detection
Rachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, Wanrong Zhang* (Alphabetical order)
NeurIPS. 2018. [paper]
Poster presentation in TPDP @CCS. 2018.


Journal Papers

A standardised differential privacy framework for epidemiological modelling with mobile phone data
Merveille Koissi Savi, Akash Yavad, Wanrong Zhang, Navin Vembar, Andrew Schroeder, Satchit Balsari, Caroline Buckee, Salil Vadhan, N. Kishore
PLOS Digital Health. 2023. [paper]

Single and Multiple Change-Point Detection with Differential Privacy
Wanrong Zhang, Sara Krehbiel, Rui Tuo, Yajun Mei, Rachel Cummings
JMLR. 2021. [paper]

Bandit Change-Point Detection for Real-Time Monitoring High-Dimensional Data Under Sampling Control
Wanrong Zhang, Yajun Mei
Technometrics. 2022. [paper]
Poster presentation in The 7th Workshop on Biostatistics and Bioinformatics. 2019.
Best Student Poster Awards for the ASA Georgia Chapter.


Workshop Papers

Training Private and Efficient Language Models with Synthetic Data from LLMs
Da Yu, Arturs Backurs, Sivakanth Gopi, Huseyin Inan, Janardhan Kulkarni, Zinan Lin, Chulin Xie, Huishuai Zhang, Wanrong Zhang
Socially Responsible Language Modelling Research (SoLaR) 2023. [paper]


White Paper

Challenges towards the Next Frontier in Privacy
Rachel Cummings, Damien Desfontaines, David Evans, Roxana Geambasu, Matthew Jagielski, Yangsibo Huang, Peter Kairouz, Gautam Kamath, Sewoong Oh, Olga Ohrimenko, Nicolas Papernot, Ryan Rogers, Milan Shen, Shuang Song, Weijie Su, Andreas Terzis, Abhradeep Thakurta, Sergei Vassilvitskii, Yu-Xiang Wang, Li Xiong, Sergey Yekhanin, Da Yu, Huanyu Zhang, Wanrong Zhang
2023. [paper]


Talks

Joint Statistical Meetings, Toronto, August 2023.
Continual Release of Differentially Private Synthetic Data

Theory and Practice of Differential Privacy Workshop, Boston, September 2023. (Invited keynote Talk)
Composition Theorems for Interactive Differential Privacy

STOC, Orlando, June 2023.
Concurrent Composition Theorems for Differential Privacy

CATT 2022 Global Analytics Conference, UT Austin, November 2022.
Composition Theorems for Interactive Differential Privacy

Societal Considerations and Applications Workshop, Simons Institute for the Theory of Computing, November 2022.
Concurrent Composition Theorems for Differential Privacy [video]

Google Privacy Seminar, August 2022.
Concurrent Composition Theorems for Differential Privacy

ICSA Applied Statistics Symposium, June 2022.
Differentially Private Approaches for Streaming Data Analysis

INFORMS ICS, Tampa, January 2022.
Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size

USENIX Security Symposium, August 2021.
Leakage of Dataset Properties in Multi-Party Machine Learning

ICML, July 2021.
PAPRIKA: Private Online False Discovery Rate Control [slides]

FORC, June 2021.
Attribute Privacy: Framework and Mechanisms
PAPRIKA: Private Online False Discovery Rate Control

Microsoft Research, February 2021.
Privacy-Preserving Statistical Tools: Differential Privacy and Beyond

CDAC Rising Stars in Data Science, January 2021.
PAPRIKA: Private Online False Discovery Rate Control

DP Lunch Seminar, Boston University, December 2020.
Differentially Private Change-point Detection

INFORMS, November, 2020.
Attribute Privacy: Framework and Mechanisms

INFORMS, November, 2020.
Bandit Change-Point Detection for Real-Time Monitoring High-Dimensional Data Under Sampling Control

ICML, July, 2020.
Privately Detecting Changes in Unknown Distributions [slides]

Cybersecurity Lecture Series, Georgia Tech, March, 2020.
Differentially Private Change-point Detection [slides]

INFORMS, Seattle, October, 2019.
Differentially Private Change-point Detection


Service


I am currently co-organizing the Boston-area data privacy seminar series.


I have been (or will be) on the program committee (i.e., a reviewer) for conferences: NeurIPS20, AAAI21, ICLR21, AISTATS21, ICML21, NeurIPS21, ICLR22, ICML22, FAccT22, COLT22, ISIT22, FAccT23, COLT23 ; and workshops: TPDP20, TPDP21, TPDP22; and journals: Journal of Applied Statistics, Statistica Sinica, Journal of Machine Learning Research, Transactions on Machine Learning Research, Computers&Security.


Teaching


CS 208: Applied Privacy for Data Science, Spring 2022

Assistantships
ISyE 6412: Theoretical Statistics, Fall 2019
ISyE 6669: Deterministic Optimization, Fall 2018
ISyE 4031: Regression and Forecasting, Spring 2018
ISyE 3039: Methods Quality Improvement, Summer 2017
ISyE 2028: Basic Statistical Methods, Spring 2017
ISyE 3770: Statistics and Applications, Fall 2016