5 citations · 12 across the 6 of their papers we have counts for
6 papers
How to DP-fy Your Data: A Practical Guide to Generating Synthetic Data With Differential Privacy
Natalia Ponomareva, Zheng Xu, H. Brendan McMahan +12
High quality data is needed to unlock the full potential of AI for end users. However finding new sources of such data is getting harder: most publicly-available human generated da…
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…
Randomization Techniques to Mitigate the Risk of Copyright Infringement
Wei-Ning Chen, Peter Kairouz, Sewoong Oh +1
In this paper, we investigate potential randomization approaches that can complement current practices of input-based methods (such as licensing data and prompt filtering) and outp…
Improved Communication-Privacy Trade-offs in Mean Estimation under Streaming Differential Privacy
Wei-Ning Chen, Berivan Isik, Peter Kairouz +3
We study mean estimation under central differential privacy and communication constraints, and address two key challenges: firstly, existing mean estimation schemes that simu…
Privacy-Preserving Instructions for Aligning Large Language Models
Da Yu, Peter Kairouz, Sewoong Oh +1
Service providers of large language model (LLM) applications collect user instructions in the wild and use them in further aligning LLMs with users' intentions. These instructions,…
User Inference Attacks on Large Language Models
Nikhil Kandpal, Krishna Pillutla, Alina Oprea +3
Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of f…