Official implementation for
- LP-BFGS attack: An adversarial attack based on Hessian with limited pixels.
For any questions, contact (zhangjiebao2014@mail.ynu.edu.cn).
- Python
- Pytorch
- Torattacks >= 3.2.6
- Torchvision
- Pytorchcv
- pytorch-minimize
- captum, IntegratedGradient implementation by Pytorch
- some datasets will be downloaded.
python attack_models.py
If you find this repo useful for your research, please consider citing the paper
@misc{lp-bfgs-attack,
doi = {10.48550/arXiv.2210.15446},
url = {https://arxiv.org/abs/2210.15446},
author = {Zhang, Jiebao and Qian, Wenhua and Nie, Rencan and Cao, Jinde and Xu, Dan},
title = {LP-BFGS attack: An adversarial attack based on the Hessian with limited pixels},
publisher = {arXiv},
year = {2022},
}