xaddwell / NAA-pytorch

Neuron Attribution-based Attacks

Improving Adversarial Transferability via Neuron Attribution-Based Attacks (CVPR 2022)

Official Tensorflow implementation for "Improving Adversarial Transferability via Neuron Attribution-based Attacks" (CVPR 2022). tensorflow

we re-implement NAA with pytorch

Citing this work

If you find this work is useful in your research, please consider citing:

@article{zhang2022improving,
  title={Improving Adversarial Transferability via Neuron Attribution-Based Attacks},
  author={Zhang, Jianping and Wu, Weibin and Huang, Jen-tse and Huang, Yizhan and Wang, Wenxuan and Su, Yuxin and Lyu, Michael R},
  journal={arXiv preprint arXiv:2204.00008},
  year={2022}
}