6.3k citations · 20.9k across the 54 of their papers we have counts for
Showing 2017Show all
2 papers · 1 filter
cs.LG2017★ 742 cited
Learning Differentially Private Recurrent Language Models
H. Brendan McMahan, Daniel Ramage, Kunal Talwar +1
We demonstrate that it is possible to train large recurrent language models with user-level differential privacy guarantees with only a negligible cost in predictive accuracy. Our…
stat.ML2017★ 39 cited
On the Protection of Private Information in Machine Learning Systems: Two Recent Approaches
Martín Abadi, Úlfar Erlingsson, Ian Goodfellow +5
The recent, remarkable growth of machine learning has led to intense interest in the privacy of the data on which machine learning relies, and to new techniques for preserving priv…