Pierre Tholoniat
Ph.D. Student in Computer Science, Columbia University

I am a Ph.D. student in computer science at Columbia University, advised by Roxana Geambasu. I did my undergrad in mathematics and computer science at Ecole Polytechnique, in France (Grande Ecole master program X2016).

I am researching security and privacy, with a focus on applied cryptography and distributed systems. I enjoy solving socially meaningful problems by building practical systems that rely on sound theoretical foundations. Lately, I have been working on privacy-preserving machine learning: I am building systems for differential privacy at Columbia University. I am also involved in open-source projects such as OpenMined.

Feel free to contact me at pierre@tholoniat.com. Here is my PGP public key. I’m also on Matrix and Signal.


For more details, please see my LinkedIn or ask me for my most recent CV.


  • Columbia University. Ph.D. in Computer Science (2021 – current). New York, NY.

  • Columbia University. M.S. in Computer Science (2019 – 2020). New York, NY.

  • École Polytechnique. B.S. in Engineering, M.S. in Engineering (2016 – 2019). Palaiseau, FR.

  • Université Paris Nanterre. B.S. in Philosophy (2017 – 2018). Nanterre, FR.

  • Lycée Sainte-Geneviève. Prépa in Mathematics and Physics (2014 – 2016). Versailles, FR.


  • École Normale Supérieure. Research Intern (2020). Paris, FR.

  • Columbia University. Teaching Assistant (2019 – 2020). New York, NY.

  • The University of Sydney. Visiting Researcher (2019). Sydney, AU.

  • Muvee Technologies. Software Engineering Intern (2018). Singapore, SG.

  • Lycée Sainte-Geneviève. Teaching Assistant (2017 – 2018). Versailles, FR.

  • French Armed Forces. Officer cadet (2016 – 2017). Tahiti, PF.


Ongoing projects

Here are my main projects:

Privacy resource scheduling and orchestration. I am working on differential privacy for machine learning workloads with Roxana Geambasu, my advisor at Columbia University. We implemented a system to manage privacy budget as a resource (akin to CPU or RAM) on Kubernetes clusters, and we are studying how to schedule this resource under various differential privacy semantics. You can check out the code for our OSDI 2021 paper here: PrivateKube.

Large scale PPML systems. I joined a team at Brookhaven National Laboratory that designs and evaluates large scale privacy-preserving machine learning systems running on top of the Department of Energy’s supercomputers.

Function secret sharing for encrypted deep learning. I am maintaining an open-source library for OpenMined. Sycret is the first Python library for function secret sharing. It relies on an efficient parallelized Rust backend using cryptographic hardware acceleration. We plugged it into PySyft, one of the leading privacy-preserving machine learning frameworks, to build ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing.

Some past projects

See my publications below for more details.

Distributed algorithms. I spent 5 months in 2019 at the Concurrent Systems Research Group of the University of Sydney, where I studied cross-chain protocols and the formal verification of distributed algorithms with Vincent Gramoli and Rob van Glabbeek. In 2020 we worked on a compositional approach to model-check consensus algorithms.

Undergraduate research. I worked on code-based proofs with EasyCrypt at Inria, designed a crypto-economic system that made it to the Blockchain Innovation Challenge, studied the annihilation of matter and antimatter at École Polytechnique’s laboratory for high energy physics, or classified periodical pavements in finite dimension through group cohomology.


Please see Semantic Scholar or Google Scholar for a more up-to-date list with files (including preprints and technical reports).

Peer-reviewed conference proceedings

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. ArXiv preprint.

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), USENIX Association, Jul. 2021, pp. 55–74, isbn: 978-1-939133-22-9. ArXiv preprint.

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, ser. SPAA ’20, New York, NY, USA: Association for Computing Machinery, Jul. 6, 2020, pp. 579–581, isbn: 978-1-4503-6935-0. ArXiv preprint, Extended version.

Peer-reviewed workshop papers

P. Tholoniat and I. Chai, “Bulletproof hosting: Ecosystem and registry-based approaches”, in 2020 Student Symposium in Cybersecurity Policy, Boston, MA, USA: Tufts University, 2020.

P. Tholoniat and V. Gramoli, “Formal verification of blockchain byzantine fault tolerance”, in 6th Workshop on Formal Reasoning in Distributed Algorithms (FRIDA’19), 2019. ArXiv preprint.

Technical reports

N. Bertrand, V. Gramoli, I. Konnov, M. Lazic, P. Tholoniat, and J. Widder, Compositional Verification of Byzantine Consensus, 2021. hal-03158911. HAL preprint.

R. van Glabbeek, V. Gramoli, and P. Tholoniat, Cross-chain payment protocols with success guarantees, 2019. arXiv: 1912.04513[cs.DC]. ArXiv preprint.