Adam-FGSM

Official code implementation for paper

• Generate Adversarial Examples by Adaptive Moment Iterative Fast Gradient Sign Method, Applied Intelligence 2022. (Paper)

For any questions, contact (zhangjiebao2014@mail.ynu.edu.cn).

Requirements

1. Python
2. Pytorch
3. Torattacks >= 3.2.6
4. Torchvision
5. Pytorchcv

Preparations

• some file paths will be created manually
• the datasets will be downloaded automatically at the first, but for ImageNet, you should sign up in the website and then log in before you start to download it.

Attack different models on different datasets

python attack_models_on_datasets.py 

Citation

If you find this repo useful for your research, please consider citing the paper

@article{zhang_generate_2022,
	title = {Generate adversarial examples by adaptive moment iterative fast gradient sign method},
	issn = {1573-7497},
	url = {https://doi.org/10.1007/s10489-022-03437-z},
	doi = {10.1007/s10489-022-03437-z},
	journaltitle = {Applied Intelligence},
	author = {Zhang, Jiebao and Qian, Wenhua and Nie, Rencan and Cao, Jinde and Xu, Dan},
	date = {2022-04-25},
}