search

robust-ml / robust-ml.github.io

A community-run reference for state-of-the-art adversarial example defenses.
https://www.robust-ml.org/
Creative Commons Attribution Share Alike 4.0 International
49 stars 7 forks source link

Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks #6

Closed aamir-mustafa closed 5 years ago

aamir-mustafa commented 5 years ago

Name: Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks

Authors: Aamir Mustafa, Salman Khan, Munawar Hayat, Roland Goecke, Jianbing Shen, Ling Shao

Paper: https://arxiv.org/abs/1904.00887

Code: https://github.com/aamir-mustafa/pcl-adversarial-defense

Venue: Under Submission

Does the code implement the robust-ml API and include pre-trained models: yes

Dataset: CIFAR-10

Threat model: robust_model.pth.tar , L_inf (Epsilon = 8/255)

Natural accuracy: 90.62%

Claims: L_inf (Epsilon = 8/255), 32.32% against PGD

anishathalye commented 5 years ago

Thank you for the submission. From a quick glance at your code, I could not find an implementation of the robustml interface. Could you please implement the model, and then we can add your paper to the website?

Also, we require claims to be phrased in terms of the perturbation bound, not based on the particular attack being used (many papers talk about why this is a reasonable thing to do, see e.g. this for one explanation).

aamir-mustafa commented 5 years ago

Thanks, I have uploaded the python script, "robust_ml.py" to my Git Repository.

anishathalye commented 5 years ago

Merged and deployed in 1757daf213c761291e1c4d443caa3cee3a38f75e.