I am a Research Scientist at Google working on privacy, safety and security.
My research is at the intersection of differential privacy, applied cryptography and distributed systems. My Ph.D. dissertation at Columbia University was on infrastructure systems for differential privacy, with applications from datacenter orchestration to a draft standard for web privacy. See my dissertation page to learn more.
More generally, I enjoy solving socially meaningful problems by building practical systems that rely on sound theoretical foundations. I also like contributing to open-source projects and web/internet standards.
Bio
I completed my Ph.D. in computer science at Columbia University in 2025, working with Asaf Cidon, Roxana Geambasu and Mathias Lécuyer. Before that, I studied mathematics and computer science at École Polytechnique, in France.
While completing my studies, I interned at Google (2024), Cloudflare (2023), Microsoft Research (2022), École Normale Supérieure (2020) and the University of Sydney (2019).
My 2-page resume (PDF) and my LinkedIn profile have more details. My name is pronounced [pjɛʁ to.lo.ɲa].
Publications
You can find my full list of publications on Google Scholar.
- P. Tholoniat, A. Caulfield, G. Cavicchioli, M. Chen, B. Case, A. Cidon,
R. Geambasu, M. Lécuyer, M. Thomson
Big Bird: Resilient Privacy Budgeting Across Untrusted
Web Domains, SOSP '26, to appear.
- R. Geambasu, M. Raykova, P. Tholoniat, T. Tiwari, L. Tsai, and W. Zhang, Engineering Robustness into Personal Agents with the AI Workflow Store, arXiv preprint, 2026.
- M. Regehr, B. Hu, E. Leeman, P. Manurangsi, P. Tholoniat, and M. Lécuyer, Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity, arXiv preprint, 2026.
- P. Tholoniat, K. Kostopoulou, M. Chowdhury, A. Cidon, R. Geambasu, M. Lécuyer, and J. Yang: DPack: Efficiency-Oriented Privacy Budget Scheduling, EuroSys '25., Mar. 2025.
- P. Tholoniat, K. Kostopoulou, P. McNeely, P. Singh Sodhi, A. Varanasi, B. Case, A. Cidon, R. Geambasu and M. Lécuyer: Cookie Monster: Efficient On-device Budgeting for Differentially-Private Ad-Measurement Systems, in 30th ACM Symposium on Operating Systems Principles (SOSP '24), Nov. 2024. doi: 10.1145/3694715.3695965. Distinguished Artifact Honorable Mention.
- P. Tholoniat, H. A. Inan, J. Kulkarni, and R. Sim, Differentially Private Training of Mixture of Experts Models, in 5th AAAI Workshop on Privacy-Preserving Artificial Intelligence (PPAI 2024), Feb. 2024.
- K. Kostopoulou, P. Tholoniat, A. Cidon, R. Geambasu, and M. Lécuyer, Turbo: Effective Caching in Differentially-Private Databases, in 29th ACM Symposium on Operating Systems Principles (SOSP '23), Oct. 2023. doi: 10.1145/3600006.3613174.
- T. Ryffel, P. Tholoniat, D. Pointcheval, and F. Bach, AriaNN: Low-interaction privacy-preserving deep learning via function secret sharing, in Proceedings on Privacy Enhancing Technologies (PETS 22), 2022. doi: 10.2478/popets-2022-0015.
- T. Luo, M. Pan, P. Tholoniat, A. Cidon, R. Geambasu, and M. Lécuyer, Privacy budget scheduling, in 15th USENIX Symposium on Operating Systems Design and Implementation (OSDI 21), 2021, https://www.usenix.org/conference/osdi21/presentation/luo.
- N. Bertrand, V. Gramoli, M. Lazić, I. Konnov, P. Tholoniat, J. Widder, Holistic Verification of Blockchain Consensus, in 36th International Symposium on Distributed Computing (DISC 22), 2022. doi: 10.4230/LIPIcs.DISC.2022.10.
- P. Tholoniat and V. Gramoli, Formal verification of blockchain byzantine fault tolerance, in Handbook on Blockchain. Springer Optimization and Its Applications, 2022. doi: 10.1007/978-3-031-07535-3_12.
- R. van Glabbeek, V. Gramoli, and P. Tholoniat, Feasibility of Cross-Chain Payment with Success Guarantees, in Proceedings of the 32nd ACM Symposium on Parallelism in Algorithms and Architectures (SPAA 20), 2020. doi: 10.1145/3350755.3400264.