bethgelab / foolbox

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX
https://foolbox.jonasrauber.de
MIT License
2.77k stars 426 forks source link

adversarial examples can not generalize well #436

Closed Jademaker8 closed 4 years ago

Jademaker8 commented 4 years ago

Dear teacher, I am a student studying adversarial samples, may I ask that the adversarial examples generated by your library do not have the ability to generalize, what is the reason, and is it my fault? For example, the FGSM method cannot fool a retrained network. Hope to get your answer,thank you very much!

FGSM_.zip

jonasrauber commented 4 years ago

Is this still relevant?