Fawkes
------
:warning: Check out our MacOS/Windows Software on our official [webpage](https://sandlab.cs.uchicago.edu/fawkes/#code).
Fawkes is a privacy protection system developed by researchers at [SANDLab](https://sandlab.cs.uchicago.edu/), University of Chicago. For more information about the project, please refer to our project [webpage](https://sandlab.cs.uchicago.edu/fawkes/). Contact us at fawkes-team@googlegroups.com.
We published an academic paper to summarize our work "[Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models](https://www.shawnshan.com/files/publication/fawkes.pdf)" at *USENIX Security 2020*.
Copyright
---------
This code is intended only for personal privacy protection or academic research.
Usage
-----
`$ fawkes`
Options:
* `-m`, `--mode` : the tradeoff between privacy and perturbation size. Select from `min`, `low`, `mid`, `high`. The higher the mode is, the more perturbation will add to the image and provide stronger protection.
* `-d`, `--directory` : the directory with images to run protection.
* `-g`, `--gpu` : the GPU id when using GPU for optimization.
* `--batch-size` : number of images to run optimization together. Change to >1 only if you have extremely powerful compute power.
* `--format` : format of the output image (png or jpg).
when --mode is `custom`:
* `--th` : perturbation threshold
* `--max-step` : number of optimization steps to run
* `--lr` : learning rate for the optimization
* `--feature-extractor` : name of the feature extractor to use
* `--separate_target` : whether select separate targets for each faces in the diectory.
### Example
`fawkes -d ./imgs --mode min`
### Tips
- The perturbation generation takes ~60 seconds per image on a CPU machine, and it would be much faster on a GPU machine. Use `batch-size=1` on CPU and `batch-size>1` on GPUs.
- Turn on separate target if the images in the directory belong to different people, otherwise, turn it off.
- Run on GPU. The current Fawkes package and binary does not support GPU. To use GPU, you need to clone this, install the required packages in `setup.py`, and replace tensorflow with tensorflow-gpu. Then you can run Fawkes by `python3 fawkes/protection.py [args]`.
![](http://sandlab.cs.uchicago.edu/fawkes/files/obama.png)
### How do I know my images are secure?
We are actively working on this. Python scripts that can test the protection effectiveness will be ready shortly.
Quick Installation
------------------
Install from [PyPI](https://pypi.org/project/fawkes/):
```
pip install fawkes
```
If you don't have root privilege, please try to install on user namespace: `pip install --user fawkes`.
Academic Research Usage
-----------------------
For academic researchers, whether seeking to improve fawkes or to explore potential vunerability, please refer to the following guide to test Fawkes.
To protect a class in a dataset, first move the label's image to a seperate location and run Fawkes. Please use `--debug` option and set `batch-size` to a reasonable number (i.e 16, 32). If the images are already cropped and aligned, then also use the `no-align` option.
Contribute to Fawkes
--------------------
If you would like to contribute to make Fawkes software better, please checkout our [project list](https://github.com/Shawn-Shan/fawkes/projects/1) which contains our TODOs. If you are confident in helping, please open a pull requests and explain the plans for your changes. We will try our best to approve asap, and once approved, you can work on it.
### Citation
```
@inproceedings{shan2020fawkes,
title={Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models},
author={Shan, Shawn and Wenger, Emily and Zhang, Jiayun and Li, Huiying and Zheng, Haitao and Zhao, Ben Y},
booktitle={Proc. of {USENIX} Security},
year={2020}
}
```
没有合适的资源?快使用搜索试试~ 我知道了~
fawkes:Fawkes,针对面部识别系统的隐私保护工具。 有关更多信息,请访问https://sandlab.cs.uchi...
共14个文件
py:10个
md:2个
gitignore:1个
需积分: 50 3 下载量 150 浏览量
2021-02-21
04:13:56
上传
评论
收藏 31KB ZIP 举报
温馨提示
福克斯 :warning: 在我们的官方上查看我们的MacOS / Windows软件。 Fawkes是由芝加哥大学研究人员开发的一种隐私保护系统。 有关该项目的更多信息,请参阅我们的项目。 通过与我们联系。 我们在USENIX Security 2020上发表了一篇学术论文,总结了我们的工作“”。 版权 此代码仅用于个人隐私保护或学术研究。 用法 $ fawkes 选项: -m , --mode :隐私和干扰大小之间的权衡。 从min , low , mid , high 。 模式越高,对图像的干扰越大,并提供更强的保护。 -d , --directory :与图片目录运行的保障。 -g ,-- --gpu :使用GPU进行优化时的GPU ID。 --batch-size :一起运行优化的图像数。 仅当您具有强大的计算能力时,才更改为> 1。 --format :输出图像的格式(pn
资源详情
资源评论
资源推荐
收起资源包目录
fawkes-master.zip (14个子文件)
fawkes-master
fawkes
utils.py 20KB
differentiator.py 17KB
__main__.py 212B
align_face.py 4KB
__init__.py 717B
README.md 2KB
detect_faces.py 31KB
protection.py 9KB
master.py 2KB
LICENSE 1KB
app
app.py 3KB
setup.py 3KB
.gitignore 244B
README.md 4KB
共 14 条
- 1
苏鲁定
- 粉丝: 23
- 资源: 4574
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0