research
∙
02/19/2023
Why Is Public Pretraining Necessary for Private Model Training?
In the privacy-utility tradeoff of a model trained on benchmark language...
share
research
∙
10/04/2022
Recycling Scraps: Improving Private Learning by Leveraging Intermediate Checkpoints
All state-of-the-art (SOTA) differentially private machine learning (DP ...
research
∙
04/20/2022
Detecting Unintended Memorization in Language-Model-Fused ASR
End-to-end (E2E) models are often being accompanied by language models (...
research
∙
04/18/2022
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Recent work has designed methods to demonstrate that model updates in AS...
research
∙
11/09/2021
The Role of Adaptive Optimizers for Honest Private Hyperparameter Selection
Hyperparameter optimization is a ubiquitous challenge in machine learnin...
research
∙
10/31/2021
Revealing and Protecting Labels in Distributed Training
Distributed learning paradigms such as federated learning often involve ...
research
∙
04/15/2021
A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It
End-to-end Automatic Speech Recognition (ASR) models are commonly traine...
research
∙
09/21/2020
Training Production Language Models without Memorizing User Data
This paper presents the first consumer-scale next-word prediction (NWP) ...
research
∙
07/13/2020
Privacy Amplification via Random Check-Ins
Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fund...
research
∙
06/12/2020
Understanding Unintended Memorization in Federated Learning
Recent works have shown that generative sequence models (e.g., language ...
research
∙
06/21/2019
Guaranteed Validity for Empirical Approaches to Adaptive Data Analysis
We design a general framework for answering adaptive statistical queries...
research
∙
05/09/2019
Differentially Private Learning with Adaptive Clipping
We introduce a new adaptive clipping technique for training learning mod...
research
∙
03/14/2018
Model-Agnostic Private Learning via Stability
We design differentially private learning algorithms that are agnostic t...
research
∙
12/28/2017