Skip to content

[Machine Learning 2023] Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

License

Notifications You must be signed in to change notification settings

HanxunH/MDAttack

Repository files navigation

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

Code for Paper "Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness" by Xingjun Ma, Linxi Jiang, Hanxun Huang, Zejia Weng, James Bailey, Yu-Gang Jiang


Evaluate MD attack

python main.py --defence [Choice from defence models] \
               --attack [MD, MDMT, MDE] \
               --eps 8 --bs 100
  • bs as batch size.
  • eps as the epsilon.
  • Defence models evaluated in the paper are available in the defence folder.
  • The following attacks are implemented ['MD', 'MDMT', 'MDE', 'PGD', 'CW', 'PGD-ODI'], Auto Attacks aviliable at this link

Citation

If you use this code in your work, please cite the accompanying paper:

@article{ma2023imbalanced,
  title={Imbalanced gradients: a subtle cause of overestimated adversarial robustness},
  author={Ma, Xingjun and Jiang, Linxi and Huang, Hanxun and Weng, Zejia and Bailey, James and Jiang, Yu-Gang},
  journal={Machine Learning},
  pages={1--26},
  year={2023},
  publisher={Springer}
}

Part of the code is based on the following repo:

About

[Machine Learning 2023] Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published