search

as791 / Adversarial-Example-Attack-and-Defense

This repository contains the implementation of three adversarial example attack methods FGSM, IFGSM, MI-FGSM and one Distillation as defense against all attacks using MNIST dataset.
116 stars 26 forks source link

Algorithm in MI-FGSM #1

Open Yip-Ge opened 3 years ago

Yip-Ge commented 3 years ago

I am not sure if the code for MI-FGSM is correct, since the gradient is expected to be calculated in each iteration rather than a single value for all iterations?

as791 commented 3 years ago

Hi @Yip-Ge, yes you are right I think 🤔 . I will try to fix this ASAP.