BriefGPT.xyz
Nov, 2019
现代机器学习中的对抗样本：一次回顾
Adversarial Examples in Modern Machine Learning: A Review
HTML
PDF
Rey Reza Wiyatno, Anqi Xu, Ousmane Dia, Archy de Berker
TL;DR
本文对机器学习模型在视觉领域中面临的对抗性攻击和防御方法进行了广泛探讨，并讨论了不同攻击和防御方法的优点和缺点。旨在提供广泛的领域覆盖和机械进攻和防御机制的直观理解。
Abstract
Recent research has found that many families of
machine learning models
are vulnerable to
adversarial examples
: inputs that are specifically designed to cause the target model to produce erroneous outputs. In thi
→