BriefGPT.xyz
Dec, 2019
标签一致的后门攻击
Label-Consistent Backdoor Attacks
HTML
PDF
Alexander Turner, Dimitris Tsipras, Aleksander Madry
TL;DR
本文利用敌对扰动和生成模型执行高效且标签一致的后门攻击，通过注入似乎合理但难以分类的输入来使模型依赖于（易于学习的）后门触发器，达到攻击的目的。
Abstract
deep neural networks
have been demonstrated to be vulnerable to
backdoor attacks
. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a
→