Shawn-Shan /fawkes
Fawkes, privacy preserving tool against facial recognition systems. More info at https://sandlab.cs.uchicago.edu/fawkes
★ 5,627⑂ 509👁 117⑃ 22● 169▤ 1
+3
日增长
5,627
stars
509
forks
117
watchers
22
prs
169
issues
1
releases
README
Fawkes ------ :warning: Check out our MacOS/Windows Software on our official webpage. Fawkes is a privacy protection system developed by researchers at SANDLab, University of Chicago. For more information about the project, please refer to our project webpage. Contact us at [email protected]. We published an academic paper to summarize our work "Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models" 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 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). Example fawkes -d ./imgs --mode low or python3 protection.py -d ./imgs --mode low 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-size1 on GPUs. - Run on GPU. The current Fawkes package and binary does not support GPU. To use GPU, you need to clone this repo, install the required packages in setup.py, and replace tensorflow with tensorflow-gpu. Then you can run Fawkes by python3 fawkes/protection.py [args]. ! 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: 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 separate 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. 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} }
Top issues
#142failed to execute script app6 comments · 2021-07-08#157mtcnn cant use gpu4 comments · 2022-01-24#138No effect on AWS Rekognition?4 comments · 2021-05-31#132fawkes 1.0.2 exception thrown4 comments · 2021-05-10#192Does this still work today?3 comments · 2026-04-05#187Cannot be run in Linux (ubuntu)3 comments · 2024-08-16#173Publish requirements.txt3 comments · 2022-11-30#191Python version need to be specified in the README.md2 comments · 2025-05-26
Latest release
Fawkes 0.3 v0.3 2020-07-30Stable release of Fawkes source code. This version has an major updated on target selection algorithm that significantly reduces the likelihood of perturbation artifacts after cloaking. If you downloaded and experimented with v0.2 or v0.1, we strongly suggest you try v0.3. For more details of what Fawkes do, checkout our webpage. We release on software in other format. mac .dmg, windows .exe, mac binary, windows binary, linux binary, Pypi package.