theFool32 / PPBA

The project page of paper: Projection & Probability-Driven Black-Box Attack [CVPR 2020]

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

This is the project page of our paper:

Projection & Probability-Driven Black-Box Attack,
Li, J., Ji, R., Liu, H., Liu, J., Zhong, B., Deng, C., & Tian, Q. CVPR 2020. arXiv

Code

Our codes are based on cg563/simple-blackbox-attack. Please refer to their repository for more details.

To run PPBA, please check main.py for ImageNet and gcv.py for Google Cloud Vision API.

Citation

If our paper helps your research, please cite it in your publications:

@InProceedings{Li_2020_CVPR,
author = {Li, Jie and Ji, Rongrong and Liu, Hong and Liu, Jianzhuang and Zhong, Bineng and Deng, Cheng and Tian, Qi},
title = {Projection & Probability-Driven Black-Box Attack},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2020}
}

Feel free to contact to the authors (lijie.32@outlook.com) or create a new issue if you find any problems.

About

The project page of paper: Projection & Probability-Driven Black-Box Attack [CVPR 2020]


Languages

Language:Python 100.0%