TPDP 2022 - Theory and Practice of Differential Privacy

Accepted Papers

Accepted papers will be presented as in-person posters or pre-recorded lightning talks. Additionally, six papers were selected as spotlight talks.

Poster Session 1:

• Spending Privacy Budget Wisely and Fairly
  Lucas Rosenblatt, Joshua Allen, Julia Stoyanovich
• FriendlyCore: Practical Differentially Private Aggregation
  Eliad Tsfadia, Edith Cohen, Haim Kaplan, Yishay Mansour, Uri Stemmer
• A Joint Exponential Mechanism For Differentially Private Top-$k$
  Jennifer Gillenwater, Matthew Joseph, Andres Munoz Medina, Mónica Ribero
• Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
  Andrew Lowy, Meisam Razaviyayn
• Numerical Composition of Differential Privacy
  Sivakanth Gopi, Yin Tat Lee, Lukas Wutschitz
• Private optimization in the interpolation regime: faster rates and hardness results
  Hilal Asi, Karan Chadha, Gary Cheng, John Duchi
• The Poisson Binomial Mechanism for Unbiased Federated Learning with Secure Aggregation
  Wei-Ning Chen, Ayfer Ozgur, Peter Kairouz
• Practical considerations on using private sampling for synthetic data
  Clément Pierquin, Bastien Zimmermann, Matthieu Boussard
• Unlocking High-Accuracy Differentially Private Image Classification through Scale
  Soham De, Leonard Berrada, Jamie Hayes, Samuel L Smith, Borja Balle
• A Private and Computationally-Efficient Estimator for Unbounded Gaussians
  Gautam Kamath, Argyris Mouzakis, Vikrant Singhal, Thomas Steinke, Jonathan Ullman
• Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space
  Lun Wang, Iosif Pinelis, Dawn Song
• Precision-based attacks and interval refining: how to break, then fix, differential privacy on finite computers
  Samuel Haney, Damien Desfontaines, Luke Hartman, Ruchit Shrestha, Michael Hay
• Pure Differential Privacy from Secure Intermediaries
  Albert Cheu, Chao Yan
• Automatic Training for Differentially Private Neural Networks: Algorithm and Theory
  Zhiqi Bu, Yu-Xiang Wang, Sheng Zha, George Karypis
• Quantifiable disparate impacts of statistical uncertainty and privacy in census-guided grants
  Ryan Steed, Terrance Liu, Steven Wu, Alessandro Acquisti
• Faster Privacy Accounting via Evolving Discretization
  Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi
• Differentially Private Fine-tuning of Language Models
  Da Yu, Saurabh Naik, Arturs Backurs, Sivakanth Gopi, Huseyin A Inan, Gautam Kamath, Janardhan Kulkarni, Yin Tat Lee, Andre Manoel, Lukas Wutschitz, Sergey Yekhanin, Huishuai Zhang
• Differentially Private Generalized Linear Models Revisited
  Raman Arora, Raef Bassily, Cristóbal A Guzmán, Michael Menart, Enayat Ullah
• Differentially Private Synthetic Control
  Saeyoung Rho, Rachel Cummings, Vishal Misra
• Histogram Estimation under User-level Privacy with Heterogeneous Data
  Yuhan Liu, Ananda Theertha Suresh, Wennan Zhu, Peter Kairouz, Marco Gruteser
• Improving Communication with End Users About Differential Privacy
  Priyanka Nanayakkara, Mary Anne Smart, Rachel Cummings, Gabriel Kaptchuk, Elissa M. Redmiles
• Differentially Private LASSO Bandit
  Apurv Shukla, Rachel Cummings
• Differentially Private Graph Learning via Sensitivity-Bounded Personalized PageRank
  Alessandro Epasto, Vahab Mirrokni, Bryan Perozzi, Anton Tsitsulin, Peilin Zhong
• Don’t look at the data! How differential privacy reconfigures data subjects, data analysts, and the practices of data science
  Jayshree Sarathy, Sophia Song, Audrey Emma Haque, Tania Schlatter, Salil Vadhan
• Noise-aware Statistical Inference with Differentially Private Synthetic data
  Ossi Räisä, Joonas Jälkö, Samuel Kaski, Antti Honkela
• Differentially Private Data Generation with Missing Data
  Shubhankar Mohapatra, Xi He, Florian Kerschbaum
• Transfer Learning in Differential Privacy's Hybrid-Model
  Refael Kohen, Or Sheffet
• On Privacy and Personalization in Cross-Silo Federated Learning
  Ken Liu, Shengyuan Hu, Steven Wu, Virginia Smith
• Robust Locally Differentially Private Graph Analysis
  Jacob Imola, Amrita Roy Chowdhury, Kamalika Chaudhuri
• PRIMO: Private Regression in Multiple Outcomes
  Seth Neel
• Private Estimation with Public Data
  Alex Bie, Gautam Kamath, Vikrant Singhal

Poster Session 2:

• Privately Estimating Graph Parameters in Sublinear time
  Jeremiah Blocki, Elena Grigorescu, Tamalika Mukherjee
• Multi-Analyst Differential Privacy for Online Query Answering
  David Anthony Pujol, Albert Sun, Brandon Fain, Ashwin Machanavajjhala
• On the Complexity of Two-Party Differential Privacy
  Iftach Haitner, Noam Mazor, Jad Silbak, Eliad Tsfadia
• Calibrating Noise when Coordinates have Different Sensitivity
  Christian Janos Lebeda, Rasmus Pagh
• Differential Privacy and Swapping: Examining De-Identification's Impact on Minority Representation and Privacy Preservation in the U.S. Census
  Miranda Christ, Sarah Radway, Steve Bellovin
• Private Convex Optimization via Exponential Mechanism
  Sivakanth Gopi, Yin Tat Lee, Daogao Liu
• Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms
  Alireza Fallah, Ali Makhdoumi, Azarakhsh Malekian, Asuman E. Ozdaglar
• Private Non-Convex Federated Learning Without a Trusted Server
  Andrew Lowy, Ali Ghafelebashi, Meisam Razaviyayn
• Strengthening Order Preserving Encryption with Differential Privacy
  Amrita Roy Chowdhury, Bolin Ding, Somesh Jha, Weiran Liu, Jingren Zhou
• Imputation under Differential Privacy
  Soumojit Das, Joerg Drechsler, Keith Merrill, Shawn Merrill
• Query Release via the Johnson Lindenstrauss Lemma
  Aleksandar Nikolov
• A Queue-based Mechanism for Unlinkability under Batched-timing Attacks
  Alexander Koujianos Goldberg, Giulia Fanti, Nihar B Shah
• Improving Differentially Private Deep Learning using Adaptive Origin Selection
  Milad Nasr, Saeed Mahloujifar, Xinyu Tang, Virat Shejwalkar, Amir Houmansadr, Prateek Mittal
• Differentially Private Partial Set Cover with Applications to Facility Location
  George Zhaoqi Li, Dung Nguyen, Anil Vullikanti
• Efficient Mean Estimation with Pure Differential Privacy via a Sum-of-Squares Exponential Mechanism
  Mahbod Majid, Gautam Kamath, Samuel Hopkins
• Widespread Underestimation of Sensitivity in Differentially Private Libraries and How to Fix It
  Sílvia Casacuberta, Michael Shoemate, Salil Vadhan, Connor Wagaman
• Modeling the Right to Be Forgotten
  Aloni Cohen, Adam Smith, Marika Swanberg, Prashant Nalini Vasudevan
• The Price of Differential Privacy under Continual Observation
  Palak Jain, Sofya Raskhodnikova, Satchit Sivakumar, Adam Smith
• To be private and robust: Differentially Private Optimizers Can Learn Adversarially Robust Models
  Zhiqi Bu, Yuan Zhang
• Integrating Differential Privacy and Contextual Integrity
  Sebastian P Benthall, Rachel Cummings
• Discrete Distribution Estimation under User-level Local Differential Privacy
  Yuhan Liu, Jayadev Acharya, Ziteng Sun
• Accuracy, Interpretability, and Differential Privacy via Explainable Boosting
  Harsha Nori, Rich Caruana, Zhiqi Bu, Judy Hanwen Shen, Janardhan Kulkarni
• The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
  Wei-Ning Chen, Christopher A. Choquette-Choo, Peter Kairouz, Ananda Theertha Suresh
• Disparate Impact in Differential Privacy from Gradient Misalignment
  Maria S Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, Jesse C Cresswell
• New Lower Bounds for Private Estimation and a Generalized Fingerprinting Lemma
  Gautam Kamath, Argyris Mouzakis, Vikrant Singhal
• Privacy-preserving predictions for large evolving graphs
  Nidhi Hegde, Gaurav Sharma
• Differentially Private Influence Maximization with Limited Data
  Amin Rahimian, Fang-Yi Yu
• Secret-Shareable Compression of Local Randomizers
  Vitaly Feldman, Kunal Talwar
• Interactive vs Non-interactive Hypothesis Testing, with Application to Concurrent Composition of Differential Privacy
  Salil Vadhan, Wanrong Zhang
• Plume: Differential Privacy at Scale
  Kareem Amin, Jennifer Gillenwater, Matthew Joseph, Alex Kulesza, Sergei Vassilvitskii
• Visualizing Privacy-Utility Trade-Offs in Differentially Private Data Releases
  Priyanka Nanayakkara, Johes Bater, Xi He, Jessica Hullman, Jennie Rogers
• From algorithmic to institutional logics: the politics of differential privacy
  Jayshree Sarathy

Pre-recorded Lightning Talks (Playlist):

• Constant Matters: Fine-grained Complexity of Differentially Private Continual Observation
  Hendrik Fichtenberger, Monika Rauch Henzinger, Jalaj Kumar Upadhyay
• Differentially private training of residual networks with scale normalisation
  Helena Klause, Alexander Ziller, Daniel Rueckert, Kerstin Hammernik, Georgios Kaissis
• Public Data-Assisted Mirror Descent for Private Model Training
  Ehsan Amid, Arun Ganesh, Rajiv Mathews, Swaroop Ramaswamy, Shuang Song, Thomas Steinke, Vinith Menon Suriyakumar, Om Thakkar, Abhradeep Guha Thakurta
• Hyperparameter Tuning with Renyi Differential Privacy
  Nicolas Papernot, Thomas Steinke
• Living with Large $\varepsilon$ via Partial Differential Privacy
  Badih Ghazi, Ravi Kumar, Pasin Manurangsi, Thomas Steinke
• SmoothNets: Optimizing CNN architecture design for differentially private deep learning
  Nicolas Walter Remerscheid, Alexander Ziller, Daniel Rueckert, Georgios Kaissis
• Evaluating the Fairness Impact of Differentially Private Synthetic Data
  Blake Bullwinkel, Kristen Grabarz, Lily Ke, Scarlett Gong, Chris Tanner, Joshua Allen
• “You Can’t Fix What You Can’t Measure”: Privately Measuring Demographic Performance Disparities in Federated Learning
  Marc Juarez, Aleksandra Korolova
• Measuring Empirical Local Differential Privacy in Federated Learning
  Marin Matsumoto, Tsubasa Takahashi, Seng Pei Liew, Masato Oguchi
• Network Shuffling: Privacy Amplification via Random Walks
  Seng Pei Liew, Tsubasa Takahashi, Shun Takagi, Fumiyuki Kato, Yang Cao, Masatoshi Yoshikawa
• DProvSQL: Privacy Provenance Framework for Differentially Private SQL Engine
  Shufan Zhang, Runchao Jiang, Xi He
• Locally private confidence sequences for bounded means via nonparametric randomized response
  Ian Waudby-Smith, Steven Wu, Aaditya Ramdas
• Differentially Private Learning with Margin Guarantees
  Raef Bassily, Mehryar Mohri, Ananda Theertha Suresh
• Toward Differentially Private Query Release for Hierarchical Data
  Terrance Liu, Steven Wu
• Thompson Sampling under Bernoulli Rewards with Local Differential Privacy
  Bo Jiang, Tianchi Zhao, Ming Li
• Differential Privacy Amplification in Quantum and Quantum-inspired Algorithms
  Armando Angrisani, Mina Doosti, Elham Kashefi
• Private Hypothesis Testing for Social Sciences
  Ajinkya K Mulay, Sean P Lane, Erin Hennes
• dpart: Differentialy Private Autoregressive Tabular, a General Framework for Synthetic Data Generation
  Sofiane Mahiou, Kai Xu, Georgi Ganev
• Towards Platform-Supported Auditing in Social Media for Public Interest
  Basileal Yoseph Imana, Aleksandra Korolova, John Heidemann

Context

Differential privacy is a promising approach to privacy-preserving data analysis. Differential privacy provides strong worst-case guarantees about the harm that a user could suffer from participating in a differentially private data analysis, but is also flexible enough to allow for a wide variety of data analyses to be performed with a high degree of utility. Having already been the subject of a decade of intense scientific study, it has also now been deployed at government agencies such as the U.S. Census Bureau and companies including Apple, Google, Facebook, and Microsoft.

Researchers in differential privacy span many distinct research communities, including algorithms, computer security, cryptography, databases, data mining, machine learning, statistics, programming languages, social sciences, and law. This workshop will bring researchers from these communities together to discuss recent developments in both the theory and practice of differential privacy.

Specific topics of interest for the workshop include (but are not limited to):

• theory of differential privacy,
• differential privacy and security,
• privacy preserving machine learning,
• differential privacy and statistics,
• differential privacy and data analysis,
• trade-offs between privacy protection and analytic utility,
• differential privacy and surveys,
• programming languages for differential privacy,
• relaxations of the differential privacy definition,
• differential privacy vs other privacy notions and methods,
• experimental studies using differential privacy,
• differential privacy implementations,
• differential privacy and policy making,
• applications of differential privacy.

Submission

The goal of TPDP is to stimulate the discussion on the relevance of differentially private data analyses in practice. For this reason, we seek contributions from different research areas of computer science and statistics.

Authors are invited to submit a short abstract (4 pages maximum, with unlimited references and appendices (only read at reviewer's discretion)) of their work. Submissions are single-blind (non-anonymized), and there is no prescribed style file (though authors should be considerate of reviewers in their selection).

Submissions will undergo a lightweight review process and will be judged on originality, relevance, interest and clarity. Submission should describe novel work or work that has already appeared elsewhere but that can stimulate the discussion between different communities at the workshop. Accepted abstracts will be presented at the workshop either as a talk or a poster.

The workshop will not have formal proceedings and is not intended to preclude later publication at another venue.

Selected papers from the workshop will be invited to submit a full version of their work for publication in a special issue of the Journal of Privacy and Confidentiality.

Call for Papers: PDF