TRACK 1: Advancing key technologies to enable practical PPDSA solutions

PDaSP Track 1: Enabling a Privacy-Preserving Data Life Cycle with Lightweight Secure Computation, Henry Corrigan-Gibbs (PI), UC Berkeley and Emma Dauterman (Co-PI), Stanford

• Alexandra Henzinger, Emma Dauterman, Henry Corrigan-Gibbs, and Dan Boneh. "Nudge: A Private Recommendations Engine." USENIX Security 2026.
• Ryan Lehmkuhl, Henry Corrigan-Gibbs, Emma Dauterman, and David J. Wu. "Heli: Heavy-Light Private Aggregation." USENIX Security 2026.

PDaSP Track 1: Practical Secure Multiparty Computations for Graph-based Intrusion Detection Systems, Yupeng Zhang (PI), University of Illinois at Urbana-Champaign and Li Zhou (Co-PI), University of California-Irvine

• Yu Zheng, Chenang Li, Zhou Li and Qingsong Wang. Convergent Privacy Framework for Multi-layer GNNs through Contractive Message Passing. Network and Distributed System Security Symposium (NDSS), February, 2026. doi: 10.14722/ndss.2026.240255

TRACK 2: Integrated and comprehensive solutions for trustworthy data sharing in application settings

PDaSP Track 2: A Holistic Privacy Preserving Collaborative Data Sharing System for Intelligent Transportation, Xuegang Ban (PI) and Angela Kitali (Co-PI), University of Washington, Yuan Hong (PI) and Song Han (Co-PI), University of Connecticut, Binghui Wang (PI), Illinois Institute of Technology and Meisam Mohammady (PI), Iowa State University

• Qin Yang, Nicholas Stout, Meisam Mohammady, Han Wang, Ayesha Samreen, Christopher Quinn, Yan Yan, Ashish Kundu, and Yuan Hong. “PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization.” CCS 2025. doi: https://doi.org/10.1145/3719027.3765151
• Shuya Feng and Yuan Hong. “DPED: Multi-Layer Noise Distillation for Privacy-Preserving Text Embeddings.” EMNLP 2025. doi: https://doi.org/10.18653/v1/2025.emnlp-main.1282
• Joshua Lee, Ali Arastehfard, Weiran Liu, Xuegang Ban, and Yuan Hong. “SecureV2X: An Efficient and Privacy-Preserving System for Vehicle-to-Everything (V2X) Applications.” SAC 2026. doi: https://doi.org/10.1145/3748522.3779738

PDaSP Track 2: Confidential Genome Imputation and Analytics (CoGIA), Hyunghoon Cho (PI), Suleyman Sahinalp (Co-PI) and Fan Zhang (Co-PI), Yale University

PDaSP Track 2: Explainable Auditing of ML Models for Privacy Violations, Bradley Malin (PI), Vanderbilt University Medical Center, Netanel Raviv (PI) and Yevgeniy Vorobeychik (Co-PI), Washington University, and Murat Kantarcioglu (PI), Virginia Polytechnic Institute and State University

PDASP Track 2: TIDES - Building a Trusted Integration Data Exchange System, Sebastian Angel (PI), Andreas Haeberlen (Co-PI), Brett Falk (Co-PI), Ryan Marcus (Co-PI) and Pratyush Mishra (Co-PI), University of Pennsylvania

PDaSP Track 2: Secure Analytics over Federated Environments for Biomedical Science (SAFE-Bio), Ronald Hutchins (PI), University of Virginia, Jelena Mirkovic (Co-PI), USC Information Sciences Institute, Paul England (Co-PI) and John Manferdelli (Co-PI), Datica Research

TRACK 3: Usable tools, and testbeds for trustworthy sharing of private or otherwise confidential data

PDaSP Track 3: Privacy-Preserving Dairy-Digitalization with Federated Learning, Miel Hostens (PI), Cornell University and Joao Dorea (Co-PI), UW-Madison

• Hostens, Miel, Sébastien Franceschini, Meike van Leerdam, et al. 2025. “The Future of Big Data and Artificial Intelligence on Dairy Farms: A Proposed Dairy Data Ecosystem.” JDS Communications 6: S9–14. https://doi.org/https://doi.org/10.3168/jdsc.2025-0843
• Liu, Enhong, Haiyu Yang, and Miel Hostens. 2025. Evaluating Small Language Models for Agentic on-Farm Decision Support Systems. https://arxiv.org/abs/2512.14043
• Liu, E., H. Yang, S. Sharma, et al. 2025. “Agents Are All You Need: Pioneering the Use of Agentic Artificial Intelligence to Embrace Large Language Models into Dairy Science.” Journal of Dairy Science 108 (12): 14038–49. https://doi.org/https://doi.org/10.3168/jds.2025-26775
• Sharma, S., Liu, E., van Leerdam, M., Hu, H., Villalobos-Barquero, R., Dorea, J. R., ... & Hostens, M. (2026). Invited review: Milking the data for value-driven dairy farming. Journal of Dairy Science

PDaSP Track 3: Testbed for Enhancing Privacy and Robustness of Federated Learning Systems, Fatima Anwar (PI), University of Massachusetts Amherst, Muhammad Ali Gulzar (PI), Virginia Polytechnic Institute and State University, and Ali Anwar (PI), University of Minnesota-Twin Cities

PDaSP: Track 3: Rigorous and Performant Differentially Private Machine Learning via OpenDP, Salil Vadhan (PI) and Flavio Calmon (Co-PI), Harvard University

PDaSP: Track 3: TEPPIT: TEstbed for Privacy-PreservIng Technologies for Data Sharing and Analysis, Jelena Mirkovic (PI), John Heidemann (Co-PI) and Jose-Luis Ambite (Co-PI), University of Southern California