BriefGPT.xyz
Jul, 2022
通过对抗示例进行成员推断攻击
Membership Inference Attacks via Adversarial Examples
HTML
PDF
Hamid Jalalzai, Elie Kadoche, Rémi Leluc, Vincent Plassier
TL;DR
本文研究机器学习与深度学习对隐私的威胁，提出了一种测量训练数据泄露的方法以及针对成员推断攻击的新型防御机制，并通过实验数据支持了研究的结论。
Abstract
The raise of
machine learning
and
deep learning
led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Suc
→