TPDP 2024 - Theory and Practice of Differential Privacy

Accepted Papers

Poster Session 1

• Private Count Release: A Simple and Scalable Approach for Private Data Analytics
  Ryan Rogers


• Some Constructions of Private, Efficient, and Optimal K-Norm and Elliptic Gaussian Noise
  Matthew Joseph, Alexander Yu


• Bounding contribution optimally for Federated Frequency Estimation under User-level Distributed Differential Privacy
  Seng Pei Liew, Tsubasa Takahashi


• Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
  Eli Chien, Haoyu Wang, Ziang Chen, Pan Li


• Local Lipschitz Filters for Bounded-Range Functions with Applications to Arbitrary Real-Valued Functions
  Jane Lange, Ephraim Linder, Sofya Raskhodnikova, Arsen Vasilyan


• On Differentially Private Subspace Estimation Without Distributional Assumptions
  Eliad Tsfadia


• Differentially Private Parameter-Efficient Fine-tuning for Large ASR Models
  Hongbin Liu, Lun Wang, Om Thakkar, Ahbradeep Thakurta, Arun Narayanan


• How Private are DP-SGD Implementations?
  Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang


• Private Fine-tuning of Large Language Models with Zeroth-order Optimization
  Xinyu Tang, Ashwinee Panda, Milad Nasr, Saeed Mahloujifar, Prateek Mittal


• Profile Reconstruction from Private Sketches
  Hao Wu, Rasmus Pagh


• New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization
  Ashwinee Panda, Xinyu Tang, Saeed Mahloujifar, Vikash Sehwag, Prateek Mittal


• Differentially Private Synthetic Data via Foundation Model APIs 2: Text
  Chulin Xie, Zinan Lin, Arturs Backurs, Sivakanth Gopi, Da Yu, Huseyin A Inan, Harsha Nori, Haotian Jiang, Huishuai Zhang, Yin Tat Lee, Bo Li, Sergey Yekhanin


• Quantifying the Per-datum Membership Leakage
  Achraf AZIZE, Debabrota BASU


• On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence
  Achraf AZIZE, Marc JOURDAN, Aymen Al Marjani, Debabrota BASU


• DPZero: Private Fine-Tuning of Language Models without Backpropagation
  Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He


• The Privacy Power of Correlated Noise in Decentralized Learning
  Youssef Allouah, Anastasia Koloskova, Aymane El Firdoussi, Martin Jaggi, Rachid Guerraoui


• Efficient and Near-Optimal Noise Generation for Streaming Differential Privacy
  Krishnamurthy (Dj) Dvijootham, H. Brendan McMahan, Krishna Pillutla, Thomas Steinke, Abhradeep Thakkurta, Krishna Pillutla


• How to Make the Gradients Small Privately: Improved Rates for Differentially Private Non-Convex Optimization
  Andrew Lowy, Jonathan Ullman, Stephen J. Wright


• Quantifying Privacy Risks of Public Statistics to Residents of Subsidized Housing
  Ryan Steed, Diana Qing, Zhiwei Steven Wu, Ryan Steed


• Better Gaussian Mechanism using Correlated Noise
  Christian Janos Lebeda


• Mean Estimation Under Heterogeneous Privacy Demands
  Syomantak Chaudhuri, Konstantin Miagkov, Thomas A. Courtade


• Private Heterogeneous Federated Learning Without a Trusted Server Revisited: Error-Optimal and Communication-Efficient Algorithms for Convex Losses
  Changyu Gao, Andrew Lowy, Stephen J. Wright, Xingyu Zhou


• The Pervasiveness of Timing Side Channels in Differential Privacy
  Zachary Ratliff, Nicolas Berrios, James Mickens, Nicolas Berrios


• PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining
  Mishaal Kazmi, Hadrien Lautraite, Alireza Akbari, Mauricio Soroco, Qiaoyue Tang, Tao Wang, Sébastien Gambs, Mathias Lécuyer


• Lower Bounds for Private Estimation of Gaussian Covariance Matrices under All Reasonable Parameter Regimes
  Victor Sanches Portella, Nick Harvey


• Locally Private and Robust Multi-Armed Bandits
  Wei Zhang, Xingyu Zhou


• Constrastive explainable clustering with differential privacy
  Dung Nguyen, Ariel Vetzler, Sarit Kraus, Anil Vullikanti


• Tukey Depth Mechanisms for Practical Private Mean Estimation
  Gavin Brown, Lydia Zakynthinou, Gavin Brown


• Differential-Privacy Capacity
  Wael Alghamdi, Shahab Asoodeh, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar


• Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
  Wei-Ning Chen, Berivan Isik, Peter Kairouz, Albert No, Sewoong Oh, Zheng Xu


• User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates
  Hilal Asi, Daogao Liu


• User Inference for Large Language Models
  Nikhil Kandpal, Krishna Pillutla, Alina Oprea, Peter Kairouz, Christopher A. Choquette-Choo, Zheng Xu


• Cohere: Managing Differential Privacy in Large Scale Systems
  Nicolas Küchler, Emanuel Opel, Hidde Lycklama, Alexander Viand, Anwar Hithnawi


• Mixtures of Gaussians are Privately Learnable with a Polynomial Number of Samples
  Mohammad Afzali, Hassan Ashtiani, Christopher Liaw


• Improved Counting under Continual Observation with Pure Differential Privacy
  Joel Daniel Andersson, Rasmus Pagh, Sahel Torkamani


• Auditing Privacy Mechanisms via Label Inference Attacks
  Robert Istvan Busa-Fekete, Travis Dick, Claudio Gentile, Andrés Muñoz Medina, Adam Smith, Marika Swanberg


• Slowly Scaling Per-Record Differential Privacy
  Brian Finley, Anthony M Caruso, Justin C Doty, Ashwin Machanavajjhala, Mikaela R Meyer, David Pujol, William Sexton, Zachary Terner


• Continual Counting with Gradual Privacy Expiration
  Joel Daniel Andersson, Monika Henzinger, Rasmus Pagh, Teresa Anna Steiner, Jalaj Upadhyay

Poster Session 2

• Navigating Privacy: Exploring Perceptions, Practices, and Challenges Among Data Privacy Experts
  Isabela Bertolini Coelho, Frauke Kreuter


• Hash-Prune-Invert: Differentially PrivateHeavy-Hitters in the Two-Server Model
  Borja Balle, James Bell, Albert Cheu, Adria Gascon, Jonathan Katz, Mariana Raykova, Phillippp Schoppmann, Thomas Steinke, Albert Cheu


• Differentially Private Sequential Learning
  Yuxin Liu, Amin Rahimian


• Metric Differential Privacy at the User-level
  Jacob Imola, Amrita Roy Chowdhury, Kamalika Chaudhuri


• DPM: Clustering Sensitive Data through Separation
  Johannes Liebenow, Yara Schütt, Tanya Braun, Marcel Gehrke, Florian Thaeter, Esfandiar Mohammadi


• Differential Privacy in Large-Scale AI Models: Ensuring Fairness and Diagnostic Accuracy in Medical Imaging
  Soroosh Tayebi Arasteh, Alexander Ziller, Daniel Truhn, Georgios Kaissis


• Differentially Private Regression via Query-Based Sufficient Statistics
  Cecilia Ferrando, Daniel Sheldon, Cecilia Ferrando


• Revealing the Underestimated Privacy of the 2020 United States Census
  Buxin Su, Weijie Su, Chendi Wang


• On the Privacy of Sublinear-Communication Jaccard Index Estimation via Min-hash Sketching
  Seung Geol Choi, Dana Dachman-Soled, Mingyu Liang, Linsheng Liu, Arkady Yerukhimovich


• ATTAXONOMY: Unpacking Differential Privacy Guarantees Against Practical Adversaries
  Rachel Cummings, Shlomi Hod, Jayshree Sarathy, Marika Swanberg


• Private PAC Learning May be Harder than Online Learning
  Mark Bun, Aloni Cohen, Rathin Desai


• A Visualization Tool to Help Technical Practitioners of Differential Privacy
  Liudas Panavas, Saeyoung Rho, Hari Bhimaraju, Wynee Pintado, Rebecca Wright, Rachel Cummings


• Differential privacy and Sublinear time are incompatible sometimes
  Jeremiah Blocki, Hendrik Fichtenberger, Elena Grigorescu, Tamalika Mukherjee


• Public-data Assisted Private Stochastic Optimization: Power and Limitations
  Enayat Ullah, Michael Menart, Raef Bassily, Cristobal Guzman, Raman Arora, Enayat Ullah


• Scalable Private Set Union Beyond Uniform Weighting
  Justin Chen, Vincent Cohen-Addad, Alessandro Epasto, Morteza Zadimoghaddan


• Instance-Optimal Private Density Estimation in the Wasserstein Distance
  Vitaly Feldman, Audra McMillan, Satchit Sivakumar, Kunal Talwar


• Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
  Martin Bertran, Shuai Tang, Michael Kearns, Jamie Heather Morgenstern, Aaron Roth, Zhiwei Steven Wu


• Enhanced Privacy-Preserving Decision Trees using Secure Multiparty Computation and Differential Privacy
  Arisa Tajima, Wei Jiang, Virendra Marathe, Hamid Mozaffari


• Membership Inference Attacks on Diffusion Models via Quantile Regression
  Shuai Tang, Zhiwei Steven Wu, Sergul Aydore, Michael Kearns, Aaron Roth


• Sample-Optimal Locally Private Hypothesis Selection and the Provable Benefits of Interactivity
  Alireza F. Pour, Hassan Ashtiani, Shahab Asoodeh


• Joint Selection: Adaptively Incorporating Public Information for Private Synthetic Data
  Miguel Fuentes, Brett Mullins, Ryan McKenna, Gerome Miklau, Daniel Sheldon, Brett Mullins


• On the Growth of Mistakes in Differentially Private Online Learning: A Lower Bound Perspective
  Daniil Dmitriev, Kristóf Szabó, Amartya Sanyal, Amartya Sanyal


• Privately Evaluating Untrusted Black-Box Functions
  Ephraim Linder, Sofya Raskhodnikova, Adam Smith, Thomas Steinke


• Querycheetah: Fast Automated Discovery of Attribute Inference Attacks Against Query-Based Systems
  Bozhidar Stevanoski, Ana-Maria Cretu, Yves-Alexandre de Montjoye


• Efficient Decision Procedures for Differential Privacy via Probabilistic Couplings
  Azadeh Farzan, Sky Li, Aleksandar Nikolov, Vishnu Nittoor


• Sublinear Space Graph Algorithms in the Continual Release Model via Sparsification
  Alessandro Epasto, Quanquan C. Liu, Tamalika Mukherjee, Felix Zhou


• Inconsistency measures for Differentially Private databases
  Shubhankar Mohapatra, Amir Gilad, Xi He, Benny Kimelfeld


• Equitable Differential Privacy
  Vasundhara Kaul, Tamalika Mukherjee


• Attack-Aware Noise Calibration for Differential Privacy
  Juan Gomez, Bogdan Kulynych, Flavio Calmon, Carmela Troncoso


• Formal Privacy Guarantees with Invariant Statistics
  Young Hyun Cho, Jordan Awan


• Differentially Private Hierarchical Heavy Hitters
  Ari Biswas, Graham Cormode, Yaron Kanza, Divesh Srivastava, Zhengyi Zhou


• Private Selection with Heterogeneous Sensitivities
  Daniela, Allegra, Audra McMillan, Lorenz


• Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages
  Hilal Asi, Vitaly Feldman, Jelani Nelson, Huy L. Nguyen, Kunal Talwar, Samson Zhou


• Scaling up the Amplified Banded Matrix Factorization Mechanism for Differentially Private ML
  Ryan McKenna


• Optimizing Discrete Noise Distributions for Renyi Differential Privacy
  Atefeh Gilani, Juan Felipe Gomez, Shahab Asoodeh, Flavio P. Calmon, Oliver Kosut, Lalitha Sankar


• Practical Considerations for Differential Privacy
  Kareem Amin, Alex Kulesza, Sergei Vassilvitskii


• Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
  Yingyu Lin, Yi-An Ma, Yu-Xiang Wang, Rachel Redberg, Zhiqi Bu


• Adapting Differentially Private Synthetic Data to Relational Databases
  Kaveh Alimohammadi, Hao Wang, Ojas Gulati, Akash Srivastava, Navid Azizan

Poster Session 3

• Private Means and the Curious Incident of the Free Lunch
  Jack Fitzsimons, James Honaker, Michael Shoemate, Vikrant Singhal


• Differentially Private Tabular Data Synthesization using Large Language Models
  Toan Tran, Li Xiong


• Synthesizing Tight Privacy and Accuracy Bounds via Weighted Model Counting
  Lisa Oakley, Steven Holtzen, Alina Oprea


• Mean Estimation Strikes Back! An Efficient Solution to Private Classification
  Yuqing Zhu, Huanyu Zhang


• Differentially Private Maximum Matching in General Graphs
  Michael Dinitz, George Li, Quanquan Liu


• Differentially Private Range Queries with Correlated Input Perturbation
  Prathamesh Dharangutte, Jie Gao, Ruobin Gong, Guanyang Wang


• Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
  Fengyu Gao, Ruiquan Huang, Jing Yang, Fengyu Gao


• Insufficient Statistics Perturbation: Stable Estimators for Private Least Squares
  Gavin Brown, Jonathan Hayase, Samuel Hopkins, Weihao Kong, Xiyang Liu, Sewoong Oh, Juan C. Perdomo, Adam Smith


• Locally Private Histograms in All Privacy Regimes
  Clément Canonne, Abigail Gentle


• Centering Policy and Practice: Research Gaps around Usable Differential Privacy
  Rachel Cummings, Jayshree Sarathy


• Private Geometric Median
  Mahdi Haghifam, Jonathan Ullman


• DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
  Junyuan Hong, Jiachen T. Wang, Chenhui Zhang, Zhangheng Li, Bo Li, Zhangyang Wang


• Elephants Do Not Forget: Differential Privacy with State Continuity for Privacy Budget
  Jiankai Jin, Chitchanok Chuengsatiansup, Toby Murray, Benjamin I. P. Rubinstein, Yuval Yarom, Olga Ohrimenko


• Near Optimal Private Measures via Linear Queries
  Cameron Musco, Christopher Musco, Lucas Rosenblatt, Apoorv Vikram Singh


• Locally Differentially Private Histogram Estimation in the Federated Setting
  Ziyu Huang, Tingting Ou, Rachel Cummings


• FedPrivSyn: Federated Differentially Private Data Synthesis
  XIZIXIANG WEI, Tianhao Wang, JING YANG, Cong Shen


• Dimension-free Private Mean Estimation for Anisotropic Gaussians
  Yuval Dagan, Michael I. Jordan, Xuelin Yang, Lydia Zakynthinou, Nikita Zhivotovskiy


• S-BDT: Distributed Differentially Private Boosted Decision Trees
  Thorsten Peinemann, Moritz Kirschte, Joshua Stock, Carlos Cotrini, Esfandiar Mohammadi


• Privacy Pitfalls and Opportunities in Imbalanced Learning
  Lucas Rosenblatt, Yuliia Lut, Eitan Turok, Marco Avella-Medina, Rachel Cummings


• On the Formal Privacy Guarantees of Synthetic Data
  Marcel Neunhoeffer, Jonathan Latner, Joerg Drechsler


• Lower Bounds for Differential Privacy Under Continual Observation and its Implications
  Edith Cohen, Xin Lyu, Jelani Nelson, Tamás Sarlós, Uri Stemmer


• Naturally Private Recommendations with Determinantal Point Processes
  Robert Pisarczyk, Jack Fitzsimons, Agustín Freitas Pasqualini, Dmitrii Usynin


• An Attack Agnostic Approach to Empirical Privacy
  Kevin Liou, Tamara Greasby, James Honaker


• Optimal Bounds on Private Graph Approximation
  Jingcheng Liu, Jalaj Upadhyay, Zongrui Zou


• Optimality of Matrix Mechanism on $\ell_p^p$-metric
  Jingcheng Liu, Jalaj Upadhyay, Zongrui Zou


• Privacy Profiles for Private Selection
  Antti Koskela, Rachel Redberg, Yu-Xiang Wang


• Efficient and Private Marginal Reconstruction with Local Non-negativity
  Brett Mullins, Miguel Fuentes, Yingtai Xiao, Daniel Kifer, Cameron Musco, Daniel Sheldon


• Differentially Private Selection from Secure Distributed Computing
  Ivan Damgård, Hannah Keller, Boel Nelson, Claudio Orlandi, Rasmus Pagh


• Universal Exact Compression of Differentially Private Mechanisms
  Yanxiao Liu, Wei-Ning Chen, Ayfer Özgür, Cheuk Ting Li


• Correlated Mechanisms for Differentially Private Distributed Mean Estimation
  Sajani Vithana, Viveck R. Cadambe, Flavio P. Calmon, Haewon Jeong


• Faster Private Minimum Spanning Trees
  Rasmus Pagh, Lukas Retschmeier


• Perturb-and-Project: Differentially Private Similarities and Marginals
  Vincent Cohen-Addad, Tommaso D'Orsi, Alessandro Epasto, Vahab Mirrokni, Peilin Zhong


• Provable Privacy with Non-Private Pre-Processing
  Yaxi Hu, Amartya Sanyal, Bernhard Schölkopf


• Group Decision-Making among Privacy-Aware Agents
  Marios Papachristou, Amin Rahimian


• Private and Personalized Frequency Estimation in a Federated Setting
  Amrith Setlur, Vitaly Feldman, Kunal Talwar


• M-Estimation Under User-Level Local Privacy Constraints
  Lekshmi Ramesh, Elise Han, Marco Avella-Medina, Cynthia Rush


• Near-Optimal Differentially Private k-Core Decomposition
  Laxman Dhulipala, Monika Henzinger, George Li, Quanquan Liu, AR Sricharan, Leqi Zhu

Call for Papers

Differential privacy (DP) is the leading framework for data analysis with rigorous privacy guarantees. In the last 18 years, it has transitioned from the realm of pure theory to large scale, real world deployments.

Differential privacy is an inherently interdisciplinary field, drawing researchers from a variety of academic communities including machine learning, statistics, security, theoretical computer science, databases, and law. The combined effort across a broad spectrum of computer science is essential for differential privacy to realize its full potential. To this end, this workshop aims to stimulate discussion among participants about both the state-of-the-art in differential privacy and the future challenges that must be addressed to make differential privacy more practical.

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

• Theory of DP
• DP and security
• Privacy preserving machine learning
• DP and statistics
• DP and data analysis
• Trade-offs between privacy protection and analytic utility
• DP and surveys
• Programming languages for DP
• Relaxations of DP
• Relation to other privacy notions and methods
• Experimental studies using DP
• DP implementations
• DP and policy making
• Applications of DP
• Reconstruction attacks and memorization

Submissions: Authors are invited to submit a short abstract of new work or work published since July 2023 (the most recent TPDP submission deadline). Submissions must be 4 pages maximum, not including references. Submissions may also include appendices, but these are only read at reviewer's discretion. There is no prescribed style file, but authors should ensure a minimum of 1-inch margins and 10pt font. Submissions are not anonymized, and should include author names and affiliations.

Submissions will undergo a lightweight review process and will be judged on originality, relevance, interest, and clarity. Based on the volume of submissions to TPDP 2023 and the workshop's capacity constraints, we expect that the review process will be somewhat more competitive than in years past. 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. In-person attendance is encouraged, though authors of accepted abstracts who cannot attend in person will be invited to submit a short video to be linked on the TPDP website.

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.