TPDP Will be Virtual
Due to the concerns for the health and safety of attendees, CCS and affiliated workshops will take place as virtual events. The workshop will be hosted on Gather.town. CCS has posted an attendee guide video, which provides a walkthrough of the Gather.town software and features.
Registered participants can access the virtual conference venue here: https://www.virtualchair.net/events/ccs2020. No additional passwords or login codes are required.
Posters
This year's TPDP posters will be divided into three poster sessions.
Poster Session 1:
- The Discrete Gaussian for Differential Privacy, by Clément Canonne, Gautam Kamath and Thomas Steinke
- Locally Private Hypothesis Selection, by Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni, Aleksandar Nikolov, Z. Steven Wu and Huanyu Zhang
- LinkedIn's Audience Engagements API: A Privacy Preserving Data Analytics System at Scale, by Ryan Rogers, Subbu Subramaniam, Sean Peng, David Durfee, Seunghyun Lee, Santosh Kumar Kancha, Shraddha Sahay and Parvez Ahammad
- Differentially Private Decomposable Submodular Maximization, by Anamay Chaturvedi, Huy Nguyen and Lydia Zakynthinou
- Private Post-GAN Boosting, by Marcel Neunhoeffer, Z. Steven Wu and Cynthia Dwork
- Efficient, Noise-Tolerant, and Private Learning via Boosting, by Marco Carmosino, Mark Bun and Jessica Sorrell
- Closure Properties for Private Classification and Online Prediction, by Noga Alon, Amos Beimel, Shay Moran and Uri Stemmer
- Overlook: Differentially Private Exploratory Visualization for Big Data, by Pratiksha Thaker, Mihai Budiu, Parikshit Gopalan, Udi Wieder and Matei Zaharia
- On the Equivalence between Online and Private Learnability beyond Binary Classification, by Young Hun Jung, Baekjin Kim and Ambuj Tewari
- Cache Me If You Can: Accuracy-Aware Inference Engine for Differentially Private Data Exploration, by Miti Mazmudar, Thomas Humphries, Matthew Rafuse and Xi He
- Bounded Leakage Differential Privacy, by Katrina Ligett, Charlotte Peale and Omer Reingold
- A Knowledge Transfer Framework for Differentially Private Sparse Learning, by Lingxiao Wang and Quanquan Gu
- Consistent Integer, Non-Negative, Hierarchical Histograms without Integer Programming, by Cynthia Dwork and Christina Ilvento
- An Empirical Study on the Intrinsic Privacy of Stochastic Gradient Descent, by Stephanie Hyland and Shruti Tople
- Encode, Shuffle, Analyze Privacy Revisited: Formalizations and Empirical Evaluation, by Úlfar Erlingsson, Vitaly Feldman, Ilya Mironov, Ananth Raghunathan, Shuang Song, Kunal Talwar and Abhradeep Thakurta
- Improving Sparse Vector Technique with Renyi Differential Privacy, by Yuqing Zhu and Yu-Xiang Wang
- Breaking the Communication-Privacy-Accuracy Trilemma, by Wei-Ning Chen, Peter Kairouz and Ayfer Özgür
- Budget Sharing for Multi-Analyst Differential Privacy, by David Pujol, Yikai Wu, Brandon Fain and Ashwin Machanavajjhala
- AdaCliP: Adaptive Clipping for Private SGD, by Venkatadheeraj Pichapati, Ananda Theertha Suresh, Felix X. Yu, Sashank J. Reddi and Sanjiv Kumar
- Private Optimization Without Constraint Violation, by Andrés Muñoz Medina, Umar Syed, Sergei Vassilvitskii and Ellen Vitercik
- Efficient Per-Example Gradient Computations in Convolutional Neural Networks, by Gaspar Rochette, Andre Manoel and Eric Tramel
- Controlling Privacy Loss in Survey Sampling, by Audra McMillan, Mark Bun, Marco Gaboardi and Joerg Drechsler
- Privacy-Preserving Community Detection under the Stochastic Block Model, by Jonathan Hehir, Aleksandra Slavkovic and Xiaoyue Niu
- Smoothed Analysis of Differentially Private and Online Learning, by Nika Haghtalab, Tim Roughgarden and Abhishek Shetty
Poster Session 2:
- Private Mean Estimation for Heavy-Tailed Distributions, by Gautam Kamath, Vikrant Singhal and Jonathan Ullman
- Private Posterior Inference Consistent with Public Information: a Case Study in Small Area Estimation from Synthetic Census Data, by Jeremy Seeman, Aleksandra Slavkovic and Matthew Reimherr
- Reasoning About Generalization via Conditional Mutual Information, by Thomas Steinke and Lydia Zakynthinou
- Understanding Gradient Clipping in Private SGD: A Geometric Perspective, by Xiangyi Chen, Z. Steven Wu and Mingyi Hong
- Privacy Amplification via Random Check-Ins, by Borja Balle, Peter Kairouz, Brendan McMahan, Om Thakkar and Abhradeep Thakurta
- Permute-and-flip: a new mechanism for differentially-private selection, by Ryan McKenna and Daniel Sheldon
- Descent-to-Delete: Gradient-Based Methods for Machine Unlearning, by Seth Neel, Aaron Roth and Saeed Sharifi-Malvajerdi
- A Better Bound Gives a Hundred Rounds: Enhanced Privacy Guarantees via f-Divergences, by Shahab Asoodeh, Jiachun Liao, Flavio Calmon, Oliver Kosut and Lalitha Sankar
- Census TopDown and the Redistricting Use Case, by Aloni Cohen, Moon Duchin, JN Matthews, Bhushan Suwal and Peter Wayner
- Interaction is Necessary for Distributed Learning with Privacy or Communication Constraints, by Yuval Dagan and Vitaly Feldman
- Fisher information under local differential privacy, by Leighton Barnes, Wei-Ning Chen and Ayfer Ozgur
- Differentially Private Assouad, Fano, and Le Cam, by Jayadev Acharya, Ziteng Sun and Huanyu Zhang
- Learning discrete distributions: user vs item-level privacy, by Yuhan Liu, Ananda Theertha Suresh, Felix Yu, Sanjiv Kumar and Michael Riley
- Efficient Privacy-Preserving Stochastic Nonconvex Optimization, by Lingxiao Wang, Bargav Jayaraman, David Evans and Quanquan Gu
- Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification, by Yingxue Zhou, Zhiwei Steven Wu and Arindam Banerjee
- Differentially private partition selection, by Damien Desfontaines, Bryant Gipson, Chinmoy Mandayam and James Voss
- Differentially Private Clustering: Tight Approximation Ratios, by Badih Ghazi, Ravi Kumar and Pasin Manurangsi
- Let's not make a fuzz about it, by Elisabet Lobo Vesga, Alejandro Russo and Marco Gaboardi
- PAPRIKA: Private Online False Discovery Rate Control, by Wanrong Zhang, Gautam Kamath and Rachel Cummings
- Oblivious Sampling Algorithms for Private Data Analysis, by Sajin Sasy and Olga Ohrimenko
- SOGDB-epsilon: Secure Outsourced Growing Database with Differentially Private Record Update, by Chenghong Wang, Kartik Nayak and Ashwin Machanavajjhala
- Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation, by Chris Waites and Rachel Cummings
- Differentially Private Sublinear Average Degree Approximation, by Harry Sivasubramaniam, Haonan Li and Xi He
- Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning, by Chong Liu, Yuqing Zhu, Kamalika Chaudhuri and Yu-Xiang Wang
Poster Session 3:
- CoinPress: Practical Private Mean and Covariance Estimation, by Sourav Biswas, Yihe Dong, Gautam Kamath and Jonathan Ullman
- Connecting Robust Shuffle Privacy and Pan-Privacy, by Victor Balcer, Albert Cheu, Matthew Joseph and Jieming Mao
- Differentially Private Variational Autoencoders with Term-wise Gradient Aggregation, by Tsubasa Takahashi, Shun Takagi, Hajime Ono and Tatsuya Komatsu
- Understanding Unintended Memorization in Federated Learning, by Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews and Francoise Beaufays
- Near Instance-Optimality in Differential Privacy, by Hilal Asi and John Duchi
- Implementing differentially private integer partitions via the exponential mechanism and Implementing Sparse Vector (two papers merged), by Christina Ilvento
- Differentially Private Simple Linear Regression, by Audra McMillan, Daniel Alabi, Jayshree Sarathy, Adam Smith and Salil Vadhan
- New Oracle-Efficient Algorithms for Private Synthetic Data Release, by Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke and Z. Steven Wu
- General-Purpose Differentially-Private Confidence Intervals, by Cecilia Ferrando, Shufan Wang and Daniel Sheldon
- Central Limit Theorem and Uncertainty Principles for Differentially Private Query Answering, by Jinshuo Dong, Linjun Zhang and Weijie Su
- Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds, by Yingxue Zhou, Xiangyi Chen, Mingyi Hong, Z. Steven Wu and Arindam Banerjee
- Minimax Rates of Estimating Approximate Differential Privacy, by Xiyang Liu and Sewoong Oh
- Really Useful Synthetic Data -- A Framework to Evaluate the Quality of Differentially Private Synthetic Data, by Christian Arnold and Marcel Neunhoeffer
- PAC learning with stable and private predictions, by Yuval Dagan and Vitaly Feldman
- Computing Local Sensitivities of Counting Queries with Joins, by Yuchao Tao, Xi He, Ashwin Machanavajjhala and Sudeepa Roy
- Efficient Reductions for Differentially Private Multi-objective Regression, by Julius Adebayo and Daniel Alabi
- The Pitfalls of Differentially Private Prediction in Healthcare, by Vinith Suriyakumar, Nicolas Papernot, Anna Goldenberg and Marzyeh Ghassemi
- Tempered Sigmoid Activations for Deep Learning with Differential Privacy, by Nicolas Papernot, Abhradeep Thakurta, Shuang Song, Steve Chien and Ulfar Erlingsson
- Revisiting Membership Inference Under Realistic Assumptions, by Bargav Jayaraman, Lingxiao Wang, David Evans and Quanquan Gu
- Attribute Privacy: Framework and Mechanisms, by Wanrong Zhang, Olga Ohrimenko and Rachel Cummings
- DuetSGX: Differential Privacy with Secure Hardware, by Phillip Nguyen, Alex Silence, David Darais and Joseph Near
- A Programming Framework for OpenDP, by Marco Gaboardi, Michael Hay and Salil Vadhan
- A One-Pass Private Sketch for Most Machine Learning Tasks, by Benjamin Coleman and Anshumali Shrivastava
- Model-Agnostic Private Learning with Domain Adaptation, by Yuqing Zhu, Chong Liu and Yu-Xiang Wang
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) of their work.
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