ResearchPapers/fawkes
ResearchPapers/fawkes
2
0
Fork 0
mirror of https://github.com/Shawn-Shan/fawkes.git synced 2024-11-09 13:41:31 +05:30
Code

Merge branch 'master' of https://github.com/Shawn-Shan/fawkes

Browse Source 
Former-commit-id: f0c762735c65492816ef3b5dc9cbbb4b8aea28c5 [formerly 8fd01229e0c09d8034705dd6e990ca685c9d9111]
Former-commit-id: a29febcba88adb22fe87b68d6eeee431695e961a
This commit is contained in:
Shawn-Shan 2020-07-08 23:10:22 -05:00
commit 93af1c998d
2 changed files with 18 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -29,9 +29,9 @@ when --mode is `custom`:
* `--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 mid`
### Tips

36
fawkes/README.md
View File

@ -1,26 +1,22 @@
# Fawkes
# Fawkes Binary
This application is built for individuals to cloak their images before uploading to the Internet. For more information about the project, please refer to our project [webpage](http://sandlab.cs.uchicago.edu/fawkes/).
If you are a developer or researcher planning to customize and modify on our existing code. Please refer to [fawkes_dev](https://github.com/Shawn-Shan/fawkes/tree/master/fawkes_dev).
If you are a developer or researcher planning to customize and modify on our existing code. Please refer to [fawkes](https://github.com/Shawn-Shan/fawkes/tree/master/).
### How to Setup
#### MAC:
* Download the binary following this [link](http://sandlab.cs.uchicago.edu/fawkes/files/fawkes_binary.zip) and unzip the download file.
* Create a directory and move all the images you wish to protect into that directory. Note the path to that directory (e.g. ~/Desktop/images).
* Open [terminal](https://support.apple.com/guide/terminal/open-or-quit-terminal-apd5265185d-f365-44cb-8b09-71a064a42125/mac) and change directory to fawkes (the unzipped folder).
* (If your MacOS is Catalina) Run `sudo spctl --master-disable` to enable running apps from unidentified developer. We are working on a solution to bypass this step.
* Run `./fawkes -d IMAGE_DIR_PATH -m low` to generate cloak for images in `IMAGE_DIR_PATH`.
* When the cloaked image is generated, it will output a `*_low_cloaked.png` image in `IMAGE_DIR_PATH`. The generation takes ~40 seconds per image depending on the hardware.
* More details on the optional parameters check out the [github repo](https://github.com/Shawn-Shan/fawkes/tree/master/).
# How do I protect my images?
#### PC:
More details coming soon. The steps should be similar to the MAC setup.
TBD
### 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}
}
```
Code implementation of the paper "[Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models](https://arxiv.org/pdf/2002.08327.pdf)", at *USENIX Security 2020*.