错别字
CHAOYUHONG opened this issue · comments
Defense methods第一个防御方法应该是Feature Squeezing而不是Feature Fqueezing吧……
谢谢提醒 我update了
advboxes / AdvBox
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.