search

BorealisAI / advertorch

A Toolbox for Adversarial Robustness Research
GNU Lesser General Public License v3.0
1.29k stars 196 forks source link

Attack on ensemble models? #88

Open taoye9 opened 3 years ago

taoye9 commented 3 years ago

Hi, first want to say thanks for your effort to make research much easier!

Recently, some papers, among which i cites two, create adversarial images on multiple models to increase transferability and success rate.

  1. Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets
  2. Delving into Transferable Adversarial Examples and Black-box Attacks

I wonder would it be possible to add this feature to this project?

gwding commented 3 years ago

For many cases, predict and loss_fn can be modified to represent an ensemble of models. Do you think this might work for your situation?