WINE 2025 Tutorial:
Differential Privacy for Strategic Information Sharing and Learning
December 8, 2025, 14:00–15:00 and 15:30–17:30
Conference Room A, Rutgers University Inn and Conference Center
Embedded Files
Organizers:
Description:
The increasing prevalence of data-driven decision making requires robust mechanisms to protect sensitive information while allowing its utility for collective benefit. Differential Privacy (DP) offers a rigorous framework for achieving strong privacy guarantees. This tutorial will explore how differential privacy can be leveraged to facilitate secure and privacy-preserving information sharing in various contexts. We will dive into the fundamental concepts of DP and discuss its application in scenarios where data are acquired, shared, aggregated, or processed to derive collective insights, ensuring individual contributions remain private.
The tutorial will cover recent advances in applying DP to practical challenges in information exchange, including methods for private estimation, learning, and inference, as well as incentive compatible and privacy-preserving mechanisms for optimal data sharing and acquisition. Attendees will gain an understanding of the trade-offs involved in designing DP mechanisms for real-world systems and learn about the techniques that enable effective information flow while mitigating privacy risks. Our discussion will highlight the importance of careful design to balance privacy with the goals of data utility, sharing, and collaborative knowledge generation, as well as open problems and research questions of interest to the WINE community in this space.
Outline:
🎯 Motivation and Foundation of Differential Privacy
🎯 Motivation and Foundation of Differential Privacy
Data Utility and Privacy Protection
Differential Privacy and Approximate Differential Privacy
Literature Overview
🔒 Differential Privacy in the Context of Information Sharing
🔒 Differential Privacy in the Context of Information Sharing
Privacy-Aware Sequential Learning
Differentially Private Distributed Estimation and Inference
💰 Markets for Privacy
💰 Markets for Privacy
Optimal Data Acquisition for Statistical Estimation
Optimal Data Acquisition with Privacy-Aware Agents
Slides:
References:
[1] Daron Acemoglu, Alireza Fallah, Ali Makhdoumi, Azarakhsh Malekian, and Asuman Ozdaglar.
How good are privacy guarantees? Platform architecture and violation of user privacy. Technical report, National Bureau of Economic Research, 2023.
[2] Konstantinos Chatzikokolakis, Miguel E Andrés, Nicolás Emilio Bordenabe, and Catuscia Palamidessi.
Broadening the scope of differential privacy using metrics. In International Symposium on Privacy Enhancing Technologies Symposium, pages 82–102. Springer, 2013.
[3] Rachel Cummings, Hadi Elzayn, Emmanouil Pountourakis, Vasilis Gkatzelis, and Juba Ziani.
Optimal data acquisition with privacy-aware agents. In 2023 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML), pages 210–224. IEEE, 2023.
[4] Alireza Fallah, Ali Makhdoumi, Azarakhsh Malekian, and Asuman Ozdaglar.
Optimal and differentially private data acquisition: Central and local mechanisms. Operations Research, 72(3):1105–1123, 2024.
[5] Guocheng Liao, Yu Su, Juba Ziani, Adam Wierman, and Jianwei Huang.
The privacy paradox and optimal bias–variance trade-offs in data acquisition. Mathematics of Operations Research, 49(4):2749–2767, 2024.
[6] Yuxin Liu and M Amin Rahimian.
Privacy-aware sequential learning. arXiv preprint arXiv:2502.19525, 2025.
[7] Kobbi Nissim, Sofya Raskhodnikova, and Adam Smith.
Smooth sensitivity and sampling in private data analysis. In Proceedings of the Thirty-ninth Annual ACM Symposium on Theory of Computing, pages 75–84, 2007.
[8] Marios Papachristou and M Amin Rahimian.
Differentially private distributed estimation and learning. IISE Transactions, 57(7):756–772, 2025.
[9] Marios Papachristou and M Amin Rahimian.
Differentially private distributed inference. medRxiv, pages 2025–03, 2025.
[10] Agarwal, Anish, Munther Dahleh, and Tuhin Sarkar.
A marketplace for data: An algorithmic solution. Proceedings of the 2019 ACM Conference on Economics and Computation. 2019.
[11] Chen, Yiling, Nicole Immorlica, Brendan Lucier, Vasilis Syrgkanis, and Juba Ziani.
Optimal data acquisition for statistical estimation. In Proceedings of the 2018 ACM Conference on Economics and Computation, pp. 27-44. 2018.
[12] Chaintreau, Augustin, Roland Maio, and Juba Ziani.
The Cost of Balanced Training-Data Production in an Online Data Market. In Proceedings of the ACM on Web Conference 2025, pp. 3523-3542. 2025.
Page updated
Report abuse