Deep Learning with Differential Privacy论文阅读

标题理解

标题言简意赅，差分隐私下的深度学习，初看标题，可以推测文章会在深度学习框架中添加噪声扰动，以实现差分隐私，可以主要关注文章的深度学习框架是怎么改变的，与传统深度学习论文有哪些区别，具体是如何实现的。

Abstract

Addressing this goal, we develop new algorithmic techniques for learning and a refined analysis of privacy costs within the framework of differential privacy.

提到建立了一种可以实现差分隐私的框架，并对隐私成本进行了精细的分析。

Our implementation and experiments demonstrate that we can train deep neural networks with non-convex objectives, under a modest privacy budget, and at a manageable cost in software complexity, training efficiency, and model quality.

并提到了这个新算法颇有成效。

Introduction

提出了三个主要工作：

1.We d