368 citations · 1.5k across the 66 of their papers we have counts for
32 papers · 1 filter
Advancing the State-of-the-Art in Empirical Privacy Auditing
Nicole Mitchell, Galen Andrew, Arun Ganesh +2
Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples. Empirical privacy auditing (EPA) quantifies th…
ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control
Yuzheng Hu, Ryan McKenna, Da Yu +4
Generating high-quality synthetic text under differential privacy (DP) is critical for training and evaluating language models without compromising user privacy. Prior work on synt…
Urania: Differentially Private Insights into AI Use
Daogao Liu, Edith Cohen, Badih Ghazi +8
We introduce , a novel framework for generating insights about LLM chatbot interactions with rigorous differential privacy (DP) guarantees. The framework employs a private…
Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?
Marika Swanberg, Ryan McKenna, Edo Roth +2
Differentially private (DP) synthetic data is a versatile tool for enabling the analysis of private data. Recent advancements in large language models (LLMs) have inspired a number…
Federated Learning in Practice: Reflections and Projections
Katharine Daly, Hubert Eichner, Peter Kairouz +3
Federated Learning (FL) is a machine learning technique that enables multiple entities to collaboratively learn a shared model without exchanging their local data. Over the past de…
Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa +12
We present the findings of the first NeurIPS competition on unlearning, which sought to stimulate the development of novel algorithms and initiate discussions on formal and robust…
Can LLMs get help from other LLMs without revealing private information?
Florian Hartmann, Duc-Hieu Tran, Peter Kairouz +2
Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Servi…
Private Federated Learning with Autotuned Compression
Enayat Ullah, Christopher A. Choquette-Choo, Peter Kairouz +1
We propose new techniques for reducing communication in private federated learning without the need for setting or tuning compression rates. Our on-the-fly methods automatically ad…
Unleashing the Power of Randomization in Auditing Differentially Private ML
Krishna Pillutla, Galen Andrew, Peter Kairouz +3
We present a rigorous methodology for auditing differentially private machine learning algorithms by adding multiple carefully designed examples called canaries. We take a first pr…
Federated Learning of Gboard Language Models with Differential Privacy
Zheng Xu, Yanxiang Zhang, Galen Andrew +5
We train language models (LMs) with federated learning (FL) and differential privacy (DP) in the Google Keyboard (Gboard). We apply the DP-Follow-the-Regularized-Leader (DP-FTRL)~\…
One-shot Empirical Privacy Estimation for Federated Learning
Galen Andrew, Peter Kairouz, Sewoong Oh +3
Privacy estimation techniques for differentially private (DP) algorithms are useful for comparing against analytical bounds, or to empirically measure privacy loss in settings wher…
Algorithms for bounding contribution for histogram estimation under user-level privacy
Yuhan Liu, Ananda Theertha Suresh, Wennan Zhu +2
We study the problem of histogram estimation under user-level differential privacy, where the goal is to preserve the privacy of all entries of any single user. We consider the het…
The Fundamental Price of Secure Aggregation in Differentially Private Federated Learning
Wei-Ning Chen, Christopher A. Choquette-Choo, Peter Kairouz +1
We consider the problem of training a dimensional model with distributed differential privacy (DP) where secure aggregation (SecAgg) is used to ensure that the server only sees…
The Skellam Mechanism for Differentially Private Federated Learning
Naman Agarwal, Peter Kairouz, Ziyu Liu
We introduce the multi-dimensional Skellam mechanism, a discrete differential privacy mechanism based on the difference of two independent Poisson random variables. To quantify its…
Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning
Virat Shejwalkar, Amir Houmansadr, Peter Kairouz +1
While recent works have indicated that federated learning (FL) may be vulnerable to poisoning attacks by compromised clients, their real impact on production FL systems is not full…
A Field Guide to Federated Optimization
Jianyu Wang, Zachary Charles, Zheng Xu +50
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy prote…
The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation
Peter Kairouz, Ziyu Liu, Thomas Steinke
We consider training models on private data that are distributed across user devices. To ensure privacy, we add on-device noise and use secure aggregation so that only the noisy su…
Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs
Antonious M. Girgis, Deepesh Data, Suhas Diggavi +2
We consider a distributed empirical risk minimization (ERM) optimization problem with communication efficiency and privacy requirements, motivated by the federated learning (FL) fr…
Fast Dimension Independent Private AdaGrad on Publicly Estimated Subspaces
Peter Kairouz, Mónica Ribero, Keith Rush +1
We revisit the problem of empirical risk minimziation (ERM) with differential privacy. We show that noisy AdaGrad, given appropriate knowledge and conditions on the subspace from w…
Privacy Amplification via Random Check-Ins
Borja Balle, Peter Kairouz, H. Brendan McMahan +2
Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. Two standard approaches, priva…
Breaking the Communication-Privacy-Accuracy Trilemma
Wei-Ning Chen, Peter Kairouz, Ayfer Özgür
Two major challenges in distributed learning and estimation are 1) preserving the privacy of the local samples; and 2) communicating them efficiently to a central server, while ach…
DP-CGAN: Differentially Private Synthetic Data and Label Generation
Reihaneh Torkzadehmahani, Peter Kairouz, Benedict Paten
Generative Adversarial Networks (GANs) are one of the well-known models to generate synthetic data including images, especially for research communities that cannot use original se…
Can You Really Backdoor Federated Learning?
Ziteng Sun, Peter Kairouz, Ananda Theertha Suresh +1
The decentralized nature of federated learning makes detecting and defending against adversarial attacks a challenging task. This paper focuses on backdoor attacks in the federated…
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent +56
Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a cen…