b'Peter Kairouz'

research

∙ 05/29/2023

Federated Learning of Gboard Language Models with Differential Privacy

We train language models (LMs) with federated learning (FL) and differen...

0 Zheng Xu, et al. ∙

research

∙ 05/29/2023

Unleashing the Power of Randomization in Auditing Differentially Private ML

We present a rigorous methodology for auditing differentially private ma...

0 Krishna Pillutla, et al. ∙

research

∙ 04/04/2023

Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation

Privacy and communication constraints are two major bottlenecks in feder...

0 Wei-Ning Chen, et al. ∙

research

∙ 03/31/2023

Differentially Private Stream Processing at Scale

We design, to the best of our knowledge, the first differentially privat...

0 Bing Zhang, et al. ∙

research

∙ 02/06/2023

One-shot Empirical Privacy Estimation for Federated Learning

Privacy auditing techniques for differentially private (DP) algorithms a...

0 Galen Andrew, et al. ∙

research

∙ 07/09/2022

The Poisson binomial mechanism for secure and private federated learning

We introduce the Poisson Binomial mechanism (PBM), a discrete differenti...

0 Wei-Ning Chen, et al. ∙

research

∙ 06/07/2022

Histogram Estimation under User-level Privacy with Heterogeneous Data

We study the problem of histogram estimation under user-level differenti...

0 Yuhan Liu, et al. ∙

research

∙ 03/07/2022

The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning

We consider the problem of training a d dimensional model with distribut...

0 Wei-Ning Chen, et al. ∙

research

∙ 01/13/2022

Privacy-Utility Trades in Crowdsourced Signal Map Obfuscation

Cellular providers and data aggregating companies crowdsource celluar si...

0 Jiang Zhang, et al. ∙

research

∙ 11/03/2021

Towards Sparse Federated Analytics: Location Heatmaps under Distributed Differential Privacy with Secure Aggregation

We design a scalable algorithm to privately generate location heatmaps o...

9 Eugene Bagdasaryan, et al. ∙

research

∙ 10/29/2021

Optimal Compression of Locally Differentially Private Mechanisms

Compressing the output of ϵ-locally differentially private (LDP) randomi...

2 Abhin Shah, et al. ∙

research

∙ 10/11/2021

The Skellam Mechanism for Differentially Private Federated Learning

We introduce the multi-dimensional Skellam mechanism, a discrete differe...

15 Naman Agarwal, et al. ∙

research

∙ 10/07/2021

Pointwise Bounds for Distribution Estimation under Communication Constraints

We consider the problem of estimating a d-dimensional discrete distribut...

0 Wei-Ning Chen, et al. ∙

research

∙ 08/29/2021

Lower Bounds for the Minimum Mean-Square Error via Neural Network-based Estimation

The minimum mean-square error (MMSE) achievable by optimal estimation of...

0 Mario Diaz, et al. ∙

research

∙ 08/23/2021

Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Federated Learning

While recent works have indicated that federated learning (FL) is vulner...

0 Virat Shejwalkar, et al. ∙

research

∙ 06/16/2021

Breaking The Dimension Dependence in Sparse Distribution Estimation under Communication Constraints

We consider the problem of estimating a d-dimensional s-sparse discrete ...

0 Wei-Ning Chen, et al. ∙

research

∙ 05/11/2021

On the Renyi Differential Privacy of the Shuffle Model

The central question studied in this paper is Renyi Differential Privacy...

5 Antonious M. Girgis, et al. ∙

research

∙ 02/12/2021

The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation

We consider training models on private data that is distributed across u...

0 Peter Kairouz, et al. ∙

research

∙ 08/17/2020

Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs

We consider a distributed empirical risk minimization (ERM) optimization...

21 Antonious M. Girgis, et al. ∙

research

∙ 08/14/2020

Dimension Independence in Unconstrained Private ERM via Adaptive Preconditioning

In this paper we revisit the problem of private empirical risk minimziat...

0 Peter Kairouz, et al. ∙

research

∙ 07/22/2020

Breaking the Communication-Privacy-Accuracy Trilemma

Two major challenges in distributed learning and estimation are 1) prese...

0 Wei-Ning Chen, et al. ∙

research

∙ 07/13/2020

Privacy Amplification via Random Check-Ins

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fund...

12 Borja Balle, et al. ∙

research

∙ 01/27/2020

DP-CGAN: Differentially Private Synthetic Data and Label Generation

Generative Adversarial Networks (GANs) are one of the well-known models ...

0 Reihaneh Torkzadehmahani, et al. ∙

research

∙ 12/10/2019

Advances and Open Problems in Federated Learning

Federated learning (FL) is a machine learning setting where many clients...

33 Peter Kairouz, et al. ∙

research

∙ 11/18/2019

Can You Really Backdoor Federated Learning?

The decentralized nature of federated learning makes detecting and defen...

0 Ziteng Sun, et al. ∙

research

∙ 11/15/2019

Generative Models for Effective ML on Private, Decentralized Datasets

To improve real-world applications of machine learning, experienced mode...

29 Sean Augenstein, et al. ∙

research

∙ 11/08/2019

Theoretical Guarantees for Model Auditing with Finite Adversaries

Privacy concerns have led to the development of privacy-preserving appro...

0 Mario Diaz, et al. ∙

research

∙ 10/31/2019

Context-Aware Local Differential Privacy

Local differential privacy (LDP) is a strong notion of privacy for indiv...

0 Jayadev Acharya, et al. ∙

research

∙ 09/27/2019

Learning Generative Adversarial RePresentations (GAP) under Fairness and Censoring Constraints

We present Generative Adversarial rePresentations (GAP) as a data-driven...

0 Jiachun Liao, et al. ∙

research

∙ 06/05/2019

A Tunable Loss Function for Classification

Recently, a parametrized class of loss functions called α-loss, α∈ [1,∞]...

0 Tyler Sypherd, et al. ∙

research

∙ 02/22/2019

Federated Heavy Hitters Discovery with Differential Privacy

The discovery of heavy hitters (most frequent items) in user-generated d...

0 Wennan Zhu, et al. ∙

research

∙ 02/12/2019

A Tunable Loss Function for Binary Classification

We present α-loss, α∈ [1,∞], a tunable loss function for binary classifi...

0 Tyler Sypherd, et al. ∙

research

∙ 09/21/2018

Understanding Compressive Adversarial Privacy

Designing a data sharing mechanism without sacrificing too much privacy ...

0 Xiao Chen, et al. ∙

research

∙ 08/04/2018

On the Optimality of the Kautz-Singleton Construction in Probabilistic Group Testing

We consider the probabilistic group testing problem where d random defec...

0 Huseyin A. Inan, et al. ∙

research

∙ 07/13/2018

Generative Adversarial Privacy

We present a data-driven framework called generative adversarial privacy...

0 Chong Huang, et al. ∙

research

∙ 04/23/2018

Siamese Generative Adversarial Privatizer for Biometric Data

State-of-the-art machine learning algorithms can be fooled by carefully ...

0 Witold Oleszkiewicz, et al. ∙

research

∙ 01/18/2018

On the Contractivity of Privacy Mechanisms

We present a novel way to compare the statistical cost of privacy mechan...

0 Mario Diaz, et al. ∙

research

∙ 10/26/2017

Context-Aware Generative Adversarial Privacy

Preserving the utility of published datasets while simultaneously provid...

0 Chong Huang, et al. ∙

research

∙ 02/24/2016

Discrete Distribution Estimation under Local Privacy

The collection and analysis of user data drives improvements in the app ...

0 Peter Kairouz, et al. ∙

Peter Kairouz

Featured Co-authors