BriefGPT.xyz
Jun, 2016
Curie: 一种保护SVM分类器免受污染攻击的方法
Curie: A method for protecting SVM Classifier from Poisoning Attack
HTML
PDF
Ricky Laishram, Vir Virander Phoha
TL;DR
本文介绍了机器学习在安全相关应用中的应用，探讨了一种针对机器学习的因果完整性攻击，提出了名为Curie的一种方法来保护SVM分类器对抗黄染攻击并且实验证明了该方法的有效性。
Abstract
machine learning
is used in a number of
security
related applications such as biometric user authentication, speaker identification etc. A type of causative integrity attack against
→