具有差分隐私的模型解释

Jun, 2020

Model Explanations with Differential Privacy

Neel Patel, Reza Shokri, Yair Zick

TL;DR使用差分隐私机制构建基于特征的模型解释，降低解释数据隐私泄露，评估差分隐私模型及其隐私机制对模型解释质量的影响。

Abstract

black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that →