BriefGPT.xyz
Apr, 2018
有毒的青蛙! 针对神经网络的目标性清标签中毒攻击
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
HTML
PDF
Ali Shafahi, W. Ronny Huang, Mahyar Najibi, Octavian Suciu, Christoph Studer...
TL;DR
本文探讨在机器学习模型中的数据污染问题,提出了基于优化的毒化方法和一种水印策略,并使用含有毒素的图片控制了图像分类器的行为。
Abstract
data poisoning
is a type of adversarial attack on
machine learning
models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores a broad c
→