Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Tholoniat, Pierre"'
Autor:
Tholoniat, Pierre, Kostopoulou, Kelly, McNeely, Peter, Sodhi, Prabhpreet Singh, Varanasi, Anirudh, Case, Benjamin, Cidon, Asaf, Geambasu, Roxana, Lécuyer, Mathias
Publikováno v:
In ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP '24), November 4-6, 2024, Austin, TX, USA. ACM, New York, NY, USA, 27 pages
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. Th
Externí odkaz:
http://arxiv.org/abs/2405.16719
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, leverag
Externí odkaz:
http://arxiv.org/abs/2402.07334
Differentially-private (DP) databases allow for privacy-preserving analytics over sensitive datasets or data streams. In these systems, user privacy is a limited resource that must be conserved with each query. We propose Turbo, a novel, state-of-the
Externí odkaz:
http://arxiv.org/abs/2306.16163
Autor:
Tholoniat, Pierre, Kostopoulou, Kelly, Chowdhury, Mosharaf, Cidon, Asaf, Geambasu, Roxana, Lécuyer, Mathias, Yang, Junfeng
Machine learning (ML) models can leak information about users, and differential privacy (DP) provides a rigorous way to bound that leakage under a given budget. This DP budget can be regarded as a new type of compute resource in workloads of multiple
Externí odkaz:
http://arxiv.org/abs/2212.13228
Autor:
Bertrand, Nathalie, Gramoli, Vincent, Konnov, Igor, Lazić, Marijana, Tholoniat, Pierre, Widder, Josef
Blockchain has recently attracted the attention of the industry due, in part, to its ability to automate asset transfers. It requires distributed participants to reach a consensus on a block despite the presence of malicious (a.k.a. Byzantine) partic
Externí odkaz:
http://arxiv.org/abs/2206.04489
Machine learning (ML) models trained on personal data have been shown to leak information about users. Differential privacy (DP) enables model training with a guaranteed bound on this leakage. Each new model trained with DP increases the bound on dat
Externí odkaz:
http://arxiv.org/abs/2106.15335
Publikováno v:
Proc. 32nd ACM Symposium on Parallelism in Algorithms and Architectures, SPAA'20, July 2020, pp. 579-581
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 p
Externí odkaz:
http://arxiv.org/abs/2007.08152
We propose AriaNN, a low-interaction privacy-preserving framework for private neural network training and inference on sensitive data. Our semi-honest 2-party computation protocol (with a trusted dealer) leverages function secret sharing, a recent li
Externí odkaz:
http://arxiv.org/abs/2006.04593
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, cros
Externí odkaz:
http://arxiv.org/abs/1912.04513
Autor:
Tholoniat, Pierre, Gramoli, Vincent
To implement a blockchain, the trend is now to integrate a non-trivial Byzantine fault tolerant consensus algorithm instead of the seminal idea of waiting to receive blocks to decide upon the longest branch. After a decade of existence, blockchains t
Externí odkaz:
http://arxiv.org/abs/1909.07453