TPDP 2021 - Theory and Practice of Differential Privacy

Posters

This year's TPDP posters will be divided into three poster sessions.

Poster Session 1:

• Differentially private training of neural networks with Langevin dynamics for calibrated predictive uncertainty
  Moritz Knolle, Alexander Ziller, Dmitrii Usynin, Rickmer Braren, Marcus R. Makowski, Daniel Rueckert, Georgios Kaissis
• Comparison of Poisson-gamma and Laplace mechanisms for differential privacy
  Harrison Quick, Kyle Chen, David DeLara
• Privacy-Preserving Keystroke Analysis using Fully Homomorphic Encryption & Differential Privacy
  Jatan Loya, Tejas Bana
• Prior-Aware Distribution Estimation for Differential Privacy
  Yuchao Tao, Johes Bater, Ashwin Machanavajjhala
• Quantum statistical query model and local differential privacy
  Armando Angrisani, Elham Kashefi
• Differentially Private Algorithms for Graphs Under Continual Observation
  Hendrik Fichtenberger, Monika Henzinger, Wolfgang Ost
• Shuffle Private Stochastic Convex Optimization
  Albert Cheu, Matthew Joseph, Jieming Mao, Binghui Peng
• Gaussian Processes with Differential Privacy
  Antti Honkela
• Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
  Gautam Kamath, Xingtu Liu, Huanyu Zhang
• Remember What You Want to Forget: Algorithms for Machine Unlearning
  Ayush Sekhari, Jayadev Acharya, Gautam Kamath, Ananda Theertha Suresh
• Privacy-induced experimentation and private causal inference
  Leon Yao, Naoise Holohan, David Arbour, Dean Eckles
• A bounded-noise mechanism for differential privacy
  Yuval Dagan, Gil Kur
• Nonparametric Differentially Private Confidence Intervals for the Median
  Jörg Drechsler, Ira Globus-Harris, Audra McMillan, Jayshree Sarathy, Adam Smith
• Statistical Privacy Guarantees of Machine Learning Preprocessing Techniques
  Ashly Lau, Jonathan Passerat-Palmbach
• Differentially Private Hamiltonian Monte Carlo
  Ossi Räisä, Antti Koskela, Antti Honkela
• Membership Inference Attacks are More Powerful Against Updated Models
  Matthew Jagielski, Stanley Wu, Alina Oprea, Jonathan Ullman, Roxana Geambasu
• Formalizing Distribution Inference Risks
  Anshuman Suri, David Evans
• Multiclass versus Binary Differentially Private PAC Learning
  Mark Bun, Marco Gaboardi, Satchit Sivakumar
• Sensitivity analysis in differentially private machine learning using hybrid automatic differentiation
  Alexander Ziller, Dmitrii Usynin, Moritz Knolle, Kritika Prakash, Andrew Trask, Marcus Makowski, Rickmer Braren, Daniel Rueckert, Georgios Kaissis
• Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods
  Terrance Liu, Giuseppe Vietri, Steven Wu
• Differentially private sparse vectors with low error, optimal space, and fast access
  Martin Aumüller, Christian Janos Lebeda, Rasmus Pagh
• PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning
  Seng Pei Liew, Tsubasa Takahashi, Michihiko Ueno
• Flexible Accuracy for Differential Privacy
  Aman Bansal, Rahul Chunduru, Deepesh Data, Manoj Prabhakaran
• Tight Accounting in the Shuffle Model of Differential Privacy
  Antti Koskela, Mikko A. Heikkilä, Antti Honkela
• Outlier-Robust Optimal Transport with Applications to Generative Modeling and Data Privacy
  Sloan Nietert, Rachel Cummings, Ziv Goldfeld
• Optimal Accounting of Differential Privacy via Characteristic Function
  Yuqing Zhu, Jinshuo Dong, Yu-Xiang Wang
• Covariance-Aware Private Mean Estimation Without Private Covariance Estimation
  Gavin R Brown, Marco Gaboardi, Adam Smith, Jonathan Ullman, Lydia Zakynthinou
• A Shuffling Framework For Local Differential Privacy
  Casey Meehan, Amrita Roy Chowdhury, Kamalika Chaudhuri, Somesh Jha

Poster Session 2:

• Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization
  Pranav Shankar Subramani, Nicholas Vadivelu, Gautam Kamath
• Differential Privacy for Black-Box Statistical Analyses
  Nitin Kohli, Paul Laskowski
• “I need a better description”: An Investigation Into User Expectations For Differential Privacy
  Gabriel Kaptchuk, Rachel Cummings, Elissa M. Redmiles
• On the Renyi Differential Privacy of the Shuffle Model
  Antonious M. Girgis, Deepesh Data, Suhas Diggavi, Ananda Theertha Suresh, Peter Kairouz
• Differentially Private Bayesian Neural Network
  Zhiqi Bu, Qiyiwen Zhang, Kan Chen, Qi Long
• Mean Estimation with User-level Privacy under Data Heterogeneity
  Rachel Cummings, Vitaly Feldman, Audra McMillan, Kunal Talwar
• Differential Secrecy for Distributed Data and Applications to Robust Differentially Secure Vector Summation
  Kunal Talwar
• Differentially Private Model Personalization
  Prateek Jain, J Keith Rush, Adam Smith, Shuang Song, Abhradeep Guha Thakurta
• Hypothesis Testing for Differentially Private Linear Regression
  Daniel Alabi, Salil Vadhan
• The Sample Complexity of Distribution-Free Parity Learning in theRobust Shuffle Model
  kobbi nissim, Chao Yan
• Computing Differential Privacy Guarantees for Heterogeneous Compositions Using FFT
  Antti Koskela, Antti Honkela
• Privately Learning Mixtures of Axis-Aligned Gaussians
  Ishaq Aden-Ali, Hassan Ashtiani, Christopher Liaw
• Improved Privacy Filters and Odometers: Time-Uniform Bounds in Privacy Composition
  Justin Whitehouse, Aaditya Ramdas, Ryan Rogers, Steven Wu
• The Shape of Edge Differential Privacy
  Siddharth Vishwanath, Jonathan Hehir
• Adapting to function difficulty and growth conditions in private optimization
  Hilal Asi, Daniel Asher Nathan Levy, John Duchi
• Concurrent Composition of Differential Privacy
  Salil Vadhan, Tianhao Wang
• Randomized Response with Prior and Applications to Learning with Label Differential Privacy
  Badih Ghazi, Noah Golowich, Ravi Kumar, Pasin Manurangsi, Chiyuan Zhang
• A Members First Approach to Enabling LinkedIn's Labor Market Insights at Scale
  Ryan Rogers, Adrian Rivera Cardoso, Koray Mancuhan, Akash Kaura, Nikhil Gahlawat, Neha Jain, Paul Ko, Parvez Ahammad
• Private Boosted Decision Trees via Smooth Re-Weighting: Simplicity is Useful
  Marco Leandro Carmosino, Vahid Reza Asadi, Mohammadmahdi Jahanara, Akbar Rafiey, Bahar Salamatian
• Solo: Enforcing Differential Privacy Without Fancy Types
  Chike Abuah, David Darais, Joseph Near
• Private Multi-Task Learning: Formulation and Applications to Federated Learning
  Shengyuan Hu, Steven Wu, Virginia Smith
• Robust and Differentially Private Covariance Estimation
  Logan Gnanapragasam, Jonathan Hayase, Sewoong Oh
• Differentially Private Histograms in the Shuffle Model from Fake Users
  Albert Cheu
• User-Level Private Learning via Correlated Sampling
  Badih Ghazi, Ravi Kumar, Pasin Manurangsi
• Bounded Space Differentially Private Quantiles
  Daniel Alabi, Omri Ben-Eliezer, Anamay Chaturvedi
• The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection
  Shubhankar Mohapatra, Sajin Sasy, Xi He, Gautam Kamath, Om Thakkar
• Differentially Private Classification via 0-1 Loss
  Ryan McKenna

Poster Session 3:

• Lossless Compression of Efficient Private Local Randomizers
  Vitaly Feldman, Kunal Talwar
• Label differential privacy via clustering
  Hossein Esfandiari, Vahab Mirrokni, Umar Syed, Sergei Vassilvitskii
• Reproducibility in Learning
  Russell Impagliazzo, Rex Lei, Jessica Sorrell
• Wide Network Learning with Differential Privacy
  Huanyu Zhang, Ilya Mironov, Meisam Hejazinia
• On the Convergence of Deep Learning with Differential Privacy
  Zhiqi Bu, Hua Wang, Qi Long, Weijie J Su
• Decision Making with Differential Privacy under a Fairness Lens
  Cuong Tran, Ferdinando Fioretto
• Improving Privacy-Preserving Deep Learning With Immediate Sensitivity
  Timothy Stevens, David Darais, Ben U Gelman, David Slater, Joseph Near
• Unbiased Statistical Estimation and Valid Confidence Sets Under Differential Privacy
  Christian Covington, Xi He, James Honaker, Gautam Kamath
• Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size
  Wanrong Zhang, Yajun Mei, Rachel Cummings
• Consistent Spectral Clustering of Network Block Models under Local Differential Privacy
  Jonathan Hehir, Aleksandra Slavkovic, Xiaoyue Niu
• Benchmarking Differentially Private Graph Algorithms
  Huiyi Ning, Sreeharsha Udayashankar, Sara Qunaibi, Karl Knopf, Xi He
• Understanding Clipped FedAvg: Convergence and Client-Level Differential Privacy
  Xinwei Zhang, Xiangyi Chen, Steven Wu, Mingyi Hong
• Privacy Amplification by Bernoulli Sampling
  Jacob Imola, Kamalika Chaudhuri
• Non-Euclidean Differentially Private Stochastic Convex Optimization
  Raef Bassily, Cristóbal A Guzmán, Anupama Nandi
• Analyzing the Differentially Private Theil-Sen Estimator for Simple Linear Regression
  Jayshree Sarathy, Salil Vadhan
• Differentially Private Quantiles
  Jennifer Gillenwater, Matthew Joseph, Alex Kulesza
• Privately Publishable Per-instance Privacy: An Extended Abstract
  Rachel Emily Redberg, Yu-Xiang Wang
• The Flajolet-Martin Sketch Itself Preserves Differential Privacy: Private Counting with Minimal Space
  Adam Smith, Shuang Song, Abhradeep Guha Thakurta
• When Is Memorization of Irrelevant Training Data Necessary for High-Accuracy Learning?
  Gavin R Brown, Mark Bun, Vitaly Feldman, Adam Smith, Kunal Talwar
• Disclosure avoidance in redistricting data: is ε = 12.2 private?
  Abraham D. Flaxman
• Privately Learning Subspaces
  Vikrant Singhal, Thomas Steinke
• Private Alternating Least Squares: Practical Private Matrix Completion with Tighter Rates
  Steve Chien, Prateek Jain, Walid Krichene, Steffen Rendle, Shuang Song, Abhradeep Guha Thakurta, Li Zhang
• Practical and Private (Deep) Learning without Sampling or Shuffling
  Peter Kairouz, Hugh Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Guha Thakurta, Zheng Xu
• Differentially Private Histograms under Continual Observation: Streaming Selection into the Unknown
  Adrian Rivera Cardoso, Ryan Rogers
• Learning with User-Level Privacy
  Daniel Asher Nathan Levy, Ziteng Sun, Kareem Amin, Satyen Kale, Alex Kulesza, Mehryar Mohri, Ananda Theertha Suresh
• TEM: High Utility Metric Differential Privacy on Text
  Ricardo Silva Carvalho, Theodore Vasiloudis, Oluwaseyi Feyisetan
• Privacy Amplification by Subsampling in Time Domain
  Tatsuki Koga, Casey Meehan, Kamalika Chaudhuri

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 + references maximum) 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