Add Fast Minimum-Norm Attack (FMN)

Harry24k / adversarial-attacks-pytorch

PyTorch implementation of adversarial attacks [torchattacks].

https://adversarial-attacks-pytorch.readthedocs.io/en/latest/index.html

MIT License

1.79k stars 337 forks source link

Add Fast Minimum-Norm Attack (FMN) #165

Open lucascionis opened 8 months ago

lucascionis commented 8 months ago

PR Type and Checklist

What kind of change does this PR introduce?

[x] ADD ATTACK
- [x] DEFAULT values of arguments should be given except model.
- [x] Classname should be given as CamelCase.
- [x] Python file name should be SMALL letters of the classname.
- [x] Add attack in init.py
- [x] Check supported_mode whether the attack supports targeted mode.
- [x] README.md should be updated.
- [x] Check WORFLOW result after PR.

Fast Minimum-Norm Attack Info

Fast Minimum-Norm Attack PyTorch implementation; works with PyTorch optimizers and schedulers and supports default and targeted mode, with L0, L1, L2 and Linf norms.

Original Code Paper

Citation.

@article{pintor2021fast,
    title={Fast minimum-norm adversarial attacks through adaptive norm constraints},
    author={Pintor, Maura and Roli, Fabio and Brendel, Wieland and Biggio, Battista},
    journal={Advances in Neural Information Processing Systems},
    volume={34},
    year={2021}
}

codecov-commenter commented 8 months ago

Codecov Report

Merging #165 (dfe601c) into master (936e86d) will decrease coverage by 0.63%. The diff coverage is 57.59%.

:exclamation: Your organization needs to install the Codecov GitHub app to enable full functionality.

@@            Coverage Diff             @@
##           master     #165      +/-   ##
==========================================
- Coverage   73.37%   72.74%   -0.63%     
==========================================
  Files          44       45       +1     
  Lines        3827     3985     +158     
  Branches      578      590      +12     
==========================================
+ Hits         2808     2899      +91     
- Misses        862      925      +63     
- Partials      157      161       +4

Files	Coverage Δ
torchattacks/__init__.py	`100.00% <100.00%> (ø)`
torchattacks/attacks/fmn.py	`57.32% <57.32%> (ø)`

Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 936e86d...dfe601c. Read the comment docs.

maurapintor commented 7 months ago

Hello @rikonaka, thank you for maintaining this library. Do you have any update on this PR? Is there something that we can do to speed up the merge?

rikonaka commented 7 months ago

Hello @rikonaka, thank you for maintaining this library. Do you have any update on this PR? Is there something that we can do to speed up the merge?

Well, all we can do now is wait 🤣. But if you have other urgent reasons for the merge, you can send an email to Harry and ask him to help merge it. As far as I know, this process may takes about 3 to 6 months. In the meantime, you can continue to check and patch the code 😁.

maurapintor commented 7 months ago

Hello @rikonaka, thank you for maintaining this library. Do you have any update on this PR? Is there something that we can do to speed up the merge?

Well, all we can do now is wait 🤣. But if you have other urgent reasons for the merge, you can send an email to Harry and ask him to help merge it. As far as I know, this process may takes about 3 to 6 months. In the meantime, you can continue to check and patch the code 😁.

Good, we will wait. Thank you ;)