120 citations · 197 across the 4 of their papers we have counts for
Showing 2018Show all
2 papers · 1 filter
cs.LG2018★ 120 cited
A General Approach to Adding Differential Privacy to Iterative Training Procedures
H. Brendan McMahan, Galen Andrew, Ulfar Erlingsson +4
In this work we address the practical challenges of training machine learning models on privacy-sensitive datasets by introducing a modular approach that minimizes changes to train…
cs.CR2018★ 10 cited
A Marauder's Map of Security and Privacy in Machine Learning
Nicolas Papernot
There is growing recognition that machine learning (ML) exposes new security and privacy vulnerabilities in software systems, yet the technical community's understanding of the nat…