2
0
mirror of https://github.com/Shawn-Shan/fawkes.git synced 2024-09-20 07:26:37 +05:30
This commit is contained in:
Shawn-Shan 2020-07-16 13:39:56 -05:00
commit b70df4dd57
2 changed files with 9 additions and 2 deletions

View File

@ -1,7 +1,7 @@
Fawkes
------
Fawkes is a privacy protection system developed by researchers at [SANDLab](http://sandlab.cs.uchicago.edu/), University of Chicago. For more information about the project, please refer to our project [webpage](http://sandlab.cs.uchicago.edu/fawkes/).
Fawkes is a privacy protection system developed by researchers at [SANDLab](http://sandlab.cs.uchicago.edu/), University of Chicago. For more information about the project, please refer to our project [webpage](http://sandlab.cs.uchicago.edu/fawkes/). Contact as at fawkes-team@googlegroups.com.
We published an academic paper to summary our work "[Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models](https://www.shawnshan.com/files/publication/fawkes.pdf)" at *USENIX Security 2020*.
@ -10,7 +10,7 @@ If you would like to use Fawkes to protect your images, please check out our bin
Copyright
---------
This code is only for personal privacy protection or academic research.
This code is intended only for personal privacy protection or academic research.
We are currently exploring the filing of a provisional patent on the Fawkes algorithm.

View File

@ -23,6 +23,13 @@ If you are a developer or researcher planning to customize and modify on our exi
* Run `protection -d IMAGE_DIR_PATH` to generate cloak for images in `IMAGE_DIR_PATH`.
* When the cloaked image is generated, it will output a `*_mid_cloaked.png` image in `IMAGE_DIR_PATH`. The generation takes ~40 seconds per image depending on the hardware.
#### Linux:
* Download the binary following this [link](http://sandlab.cs.uchicago.edu/fawkes/files/fawkes_binary_linux.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 and change directory to protection (the unzipped folder).
* Run `./protection -d IMAGE_DIR_PATH` to generate cloak for images in `IMAGE_DIR_PATH`.
* When the cloaked image is generated, it will output a `*_mid_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/).