collaborators

8 papers

cs.CR20261 cited

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…

cs.LG2026

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…

cs.LG2026

JAX-Privacy: A library for differentially private machine learning

Ryan McKenna, Galen Andrew, Borja Balle +6

JAX-Privacy is a library designed to simplify the deployment of robust and performant mechanisms for differentially private machine learning. Guided by design principles of usabili…

cs.CR2026

Mayfly: Private Aggregate Insights from Ephemeral Streams of On-Device User Data

Christopher Bian, Albert Cheu, Stanislav Chiknavaryan +12

This paper introduces Mayfly, a federated analytics approach enabling aggregate queries over ephemeral on-device data streams without central persistence of sensitive user data. Ma…

cs.LG2026

Privately Fine-Tuned LLMs Preserve Temporal Dynamics in Tabular Data

Lucas Rosenblatt, Peihan Liu, Ryan McKenna +1

Research on differentially private synthetic tabular data has largely focused on independent and identically distributed rows where each record corresponds to a unique individual.…

cs.CR2025

Benchmarking Differentially Private Tabular Data Synthesis

Kai Chen, Xiaochen Li, Chen Gong +2

Differentially private (DP) tabular data synthesis generates artificial data that preserves the statistical properties of private data while safeguarding individual privacy. The em…