Pierre Tholoniat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Pierre Tholoniat has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Asaf Cidon
Columbia University, New York, USA
4 shared publications - Mathias Lécuyer
University of British Columbia, Vancouver, Canada
4 shared publications - Roxana Geambasu
Columbia University, New York, USA
4 shared publications - Kelly Kostopoulou
Columbia University, New York City, NY, USA
3 shared publications - Vincent Gramoli
University of Sydney, Sydney, Australia
2 shared publications - Alison Caulfield
Columbia University, New York, USA
1 shared publication
Latest Publications
- Open Access
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 90-124
Big Bird: Resilient Privacy Budgeting Across Untrusted Web Domains
The W3C Attribution API is an emerging standard for privacy-preserving advertising measurement. Its current privacy architecture enforces individual differential privacy (IDP) independently for each domain (e.g., an advertiser) issuing queries. We show that this guarantee is unsound under realistic system behavior: it fails under cross-querier data adaptivity and can also fail when shared limits are enforced across queriers. The issue is not the on-device accounting model itself - device-epoch IDP - but treating each querying domain in isolation. We propose Big Bird, a privacy-budget manager that makes global device-epoch IDP - enforced jointly across all domains - both sound and deployable for Attribution. Big Bird addresses the main obstacle to global enforcement in open multi-querier systems: denial-of-service depletion of a shared global budget by Sybil web domains. Its key insight is that benign Attribution workloads have a stock-and-flow structure: impressions create potential privacy loss, conversions realize it, and meaningful budget consumption should be tied to genuine user actions across distinct web domains. Big Bird enforces this structure with privacy-loss-based quotas on impression and conversion sites and a per-user-action cap on how many quotas can be activated, ensuring that adversarial impact scales with genuine user interactions rather than with the number of Sybil domains. We implement Big Bird in Rust, integrate it into Firefox's Attribution prototype, and evaluate it theoretically and empirically on real ad-tech data. We show that Big Bird provides rigorous global device-epoch IDP, formal resilience to depletion attacks, and utility for benign queriers under attack.
- 28 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 90-124
Open AccessBig Bird: Resilient Privacy Budgeting Across Untrusted Web Domains
The W3C Attribution API is an emerging standard for privacy-preserving advertising measurement. Its current privacy architecture enforces individual differential privacy (IDP) independently for each domain (e.g., an advertiser) issuing queries. We show that this guarantee is unsound under realistic system behavior: it fails under cross-querier data adaptivity and can also fail when shared limits are enforced across queriers. The issue is not the on-device accounting model itself - device-epoch IDP - but treating each querying domain in isolation. We propose Big Bird, a privacy-budget manager that makes global device-epoch IDP - enforced jointly across all domains - both sound and deployable for Attribution. Big Bird addresses the main obstacle to global enforcement in open multi-querier systems: denial-of-service depletion of a shared global budget by Sybil web domains. Its key insight is that benign Attribution workloads have a stock-and-flow structure: impressions create potential privacy loss, conversions realize it, and meaningful budget consumption should be tied to genuine user actions across distinct web domains. Big Bird enforces this structure with privacy-loss-based quotas on impression and conversion sites and a per-user-action cap on how many quotas can be activated, ensuring that adversarial impact scales with genuine user interactions rather than with the number of Sybil domains. We implement Big Bird in Rust, integrate it into Firefox's Attribution prototype, and evaluate it theoretically and empirically on real ad-tech data. We show that Big Bird provides rigorous global device-epoch IDP, formal resilience to depletion attacks, and utility for benign queriers under attack.
- Open Access
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1194-1209
DPack: Efficiency-Oriented Privacy Budget Scheduling
- 30 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 1194-1209
Open AccessDPack: Efficiency-Oriented Privacy Budget Scheduling
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 693-708
Cookie Monster: Efficient On-Device Budgeting for Differentially-Private Ad-Measurement Systems
With the impending removal of third-party cookies from major browsers and the introduction of new privacy-preserving advertising APIs, the research community has a timely opportunity to assist industry in qualitatively improving the Web's privacy. This paper discusses our efforts, within a W3C community group, to enhance existing privacy-preserving advertising measurement APIs. We analyze designs from Google, Apple, Meta and Mozilla, and augment them with a more rigorous and efficient differential privacy (DP) budgeting component. Our approach, called Cookie Monster, enforces well-defined DP guarantees and enables advertisers to conduct more private measurement queries accurately. By framing the privacy guarantee in terms of an individual form of DP, we can make DP budgeting more efficient than in current systems that use a traditional DP definition. We incorporate Cookie Monster into Chrome and evaluate it on microbenchmarks and advertising datasets. Across workloads, Cookie Monster significantly outperforms baselines in enabling more advertising measurements under comparable DP protection.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 693-708
Open AccessCookie Monster: Efficient On-Device Budgeting for Differentially-Private Ad-Measurement Systems
With the impending removal of third-party cookies from major browsers and the introduction of new privacy-preserving advertising APIs, the research community has a timely opportunity to assist industry in qualitatively improving the Web's privacy. This paper discusses our efforts, within a W3C community group, to enhance existing privacy-preserving advertising measurement APIs. We analyze designs from Google, Apple, Meta and Mozilla, and augment them with a more rigorous and efficient differential privacy (DP) budgeting component. Our approach, called Cookie Monster, enforces well-defined DP guarantees and enables advertisers to conduct more private measurement queries accurately. By framing the privacy guarantee in terms of an individual form of DP, we can make DP budgeting more efficient than in current systems that use a traditional DP definition. We incorporate Cookie Monster into Chrome and evaluate it on microbenchmarks and advertising datasets. Across workloads, Cookie Monster significantly outperforms baselines in enabling more advertising measurements under comparable DP protection.
- Open Access
Differentially Private Training of Mixture of Experts Models
This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of parameters, leveraging expansive datasets, they exhibit enhanced linguistic capabilities and emergent abilities. However, this growth raises significant computational and privacy concerns. Our study addresses these issues by exploring the potential of MoE models, known for their computational efficiency, and the application of DP, a standard for privacy preservation. We present the first known attempt to train MoE models under the constraints of DP, addressing the unique challenges posed by their architecture and the complexities of DP integration. Our initial experimental studies demonstrate that MoE models can be effectively trained with DP, achieving performance that is competitive with their non-private counterparts. This initial study aims to provide valuable insights and ignite further research in the domain of privacy-preserving MoE models, softly laying the groundwork for prospective developments in this evolving field.
Open AccessDifferentially Private Training of Mixture of Experts Models
This position paper investigates the integration of Differential Privacy (DP) in the training of Mixture of Experts (MoE) models within the field of natural language processing. As Large Language Models (LLMs) scale to billions of parameters, leveraging expansive datasets, they exhibit enhanced linguistic capabilities and emergent abilities. However, this growth raises significant computational and privacy concerns. Our study addresses these issues by exploring the potential of MoE models, known for their computational efficiency, and the application of DP, a standard for privacy preservation. We present the first known attempt to train MoE models under the constraints of DP, addressing the unique challenges posed by their architecture and the complexities of DP integration. Our initial experimental studies demonstrate that MoE models can be effectively trained with DP, achieving performance that is competitive with their non-private counterparts. This initial study aims to provide valuable insights and ignite further research in the domain of privacy-preserving MoE models, softly laying the groundwork for prospective developments in this evolving field.
- Open Access
- 23 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 579-594
Turbo: Effective Caching in Differentially-Private Databases
- 23 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 579-594
Open AccessTurbo: Effective Caching in Differentially-Private Databases
- Open Access
- 8 April 2023
- Published by Springer Nature in Distributed Computing
- Vol. 36 (2) , 137-157
Cross-chain payment protocols with success guarantees
In this paper, we consider the problem of cross-chain payment whereby customers of different escrows—implemented by a bank or a blockchain smart contract—successfully transfer digital assets without trusting each other. Prior to this work, cross-chain payment problems did not require this success, or any form of progress. We introduce a new specification formalism called Asynchronous Networks of Timed Automata to formalise such protocols. We present the first cross-chain payment protocol that ensures termination in a bounded amount of time and works correctly in the presence of clock drift. We then demonstrate that it is impossible to solve this problem without assuming synchrony, in the sense that each message is guaranteed to arrive within a known amount of time. Yet, we solve an eventually terminating weaker variant of this problem, where success is conditional on the patience of the participants, without assuming synchrony, and in the presence of Byzantine failures. We also discuss the relation with the recently defined cross-chain deals.
- 8 April 2023
- Published by Springer Nature in Distributed Computing
- Vol. 36 (2) , 137-157
Open AccessCross-chain payment protocols with success guarantees
In this paper, we consider the problem of cross-chain payment whereby customers of different escrows—implemented by a bank or a blockchain smart contract—successfully transfer digital assets without trusting each other. Prior to this work, cross-chain payment problems did not require this success, or any form of progress. We introduce a new specification formalism called Asynchronous Networks of Timed Automata to formalise such protocols. We present the first cross-chain payment protocol that ensures termination in a bounded amount of time and works correctly in the presence of clock drift. We then demonstrate that it is impossible to solve this problem without assuming synchrony, in the sense that each message is guaranteed to arrive within a known amount of time. Yet, we solve an eventually terminating weaker variant of this problem, where success is conditional on the patience of the participants, without assuming synchrony, and in the presence of Byzantine failures. We also discuss the relation with the recently defined cross-chain deals.
- 4 November 2022
- Published by Springer Nature
- p. 389-412
Formal Verification of Blockchain Byzantine Fault Tolerance
- 4 November 2022
- Published by Springer Nature
- p. 389-412
Formal Verification of Blockchain Byzantine Fault Tolerance