{"id":13488390,"url":"https://github.com/Shawn-Shan/fawkes","last_synced_at":"2025-03-28T00:33:46.074Z","repository":{"id":37247897,"uuid":"264782257","full_name":"Shawn-Shan/fawkes","owner":"Shawn-Shan","description":"Fawkes, privacy preserving tool against facial recognition systems. More info at https://sandlab.cs.uchicago.edu/fawkes","archived":false,"fork":false,"pushed_at":"2023-08-02T16:26:04.000Z","size":387,"stargazers_count":5323,"open_issues_count":42,"forks_count":491,"subscribers_count":115,"default_branch":"master","last_synced_at":"2025-03-27T05:05:41.867Z","etag":null,"topics":["adversarial-machine-learning","face-recognition","privacy-enhancing-technologies","privacy-protection"],"latest_commit_sha":null,"homepage":"https://sandlab.cs.uchicago.edu/fawkes","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Shawn-Shan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2020-05-18T00:16:49.000Z","updated_at":"2025-03-26T11:58:35.000Z","dependencies_parsed_at":"2022-07-09T13:00:31.271Z","dependency_job_id":"2bc5d0b6-4646-4fc0-9b43-3c97be99e4d8","html_url":"https://github.com/Shawn-Shan/fawkes","commit_stats":{"total_commits":115,"total_committers":4,"mean_commits":28.75,"dds":0.04347826086956519,"last_synced_commit":"aedaa82d22504c4e7dbc86de869a6e0d943a5f2a"},"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shawn-Shan%2Ffawkes","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shawn-Shan%2Ffawkes/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shawn-Shan%2Ffawkes/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shawn-Shan%2Ffawkes/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Shawn-Shan","download_url":"https://codeload.github.com/Shawn-Shan/fawkes/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245949289,"owners_count":20698913,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["adversarial-machine-learning","face-recognition","privacy-enhancing-technologies","privacy-protection"],"created_at":"2024-07-31T18:01:14.860Z","updated_at":"2025-03-28T00:33:46.007Z","avatar_url":"https://github.com/Shawn-Shan.png","language":"Python","funding_links":[],"categories":["Cloaking","Python","Sensor Processing","Awesome Privacy Engineering [![Awesome](https://awesome.re/badge.svg)](https://awesome.re)","📦 Legacy \u0026 Inactive Projects"],"sub_categories":["Images","Image Processing","Facial Recognition"],"readme":"Fawkes\n------\n:warning: Check out our MacOS/Windows Software on our official [webpage](https://sandlab.cs.uchicago.edu/fawkes/#code).\n\nFawkes is a privacy protection system developed by researchers at [SANDLab](https://sandlab.cs.uchicago.edu/),\nUniversity of Chicago. For more information about the project, please refer to our\nproject [webpage](https://sandlab.cs.uchicago.edu/fawkes/). Contact us at fawkes-team@googlegroups.com.\n\nWe published an academic paper to summarize our\nwork \"[Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models](https://www.shawnshan.com/files/publication/fawkes.pdf)\"\nat *USENIX Security 2020*.\n\n\nCopyright\n---------\nThis code is intended only for personal privacy protection or academic research.\n\nUsage\n-----\n\n`$ fawkes`\n\nOptions:\n\n* `-m`, `--mode`       : the tradeoff between privacy and perturbation size. Select from `low`, `mid`, `high`. The\n  higher the mode is, the more perturbation will add to the image and provide stronger protection.\n* `-d`, `--directory`  : the directory with images to run protection.\n* `-g`, `--gpu`        : the GPU id when using GPU for optimization.\n* `--batch-size`       : number of images to run optimization together. Change to \u003e1 only if you have extremely powerful\n  compute power.\n* `--format`      : format of the output image (png or jpg).\n\n### Example\n\n`fawkes -d ./imgs --mode low`\n\nor `python3 protection.py -d ./imgs --mode low`\n\n\n### Tips\n\n- The perturbation generation takes ~60 seconds per image on a CPU machine, and it would be much faster on a GPU\n  machine. Use `batch-size=1` on CPU and `batch-size\u003e1` on GPUs.\n- Run on GPU. The current Fawkes package and binary does not support GPU. To use GPU, you need to clone this repo, install\n  the required packages in `setup.py`, and replace tensorflow with tensorflow-gpu. Then you can run Fawkes\n  by `python3 fawkes/protection.py [args]`.\n\n![](http://sandlab.cs.uchicago.edu/fawkes/files/obama.png)\n\n### How do I know my images are secure?\n\nWe are actively working on this. Python scripts that can test the protection effectiveness will be ready shortly.\n\nQuick Installation\n------------------\n\nInstall from [PyPI](https://pypi.org/project/fawkes/):\n\n```\npip install fawkes\n```\n\nIf you don't have root privilege, please try to install on user namespace: `pip install --user fawkes`.\n\n\nAcademic Research Usage\n-----------------------\nFor academic researchers, whether seeking to improve fawkes or to explore potential vunerability, please refer to the\nfollowing guide to test Fawkes.\n\nTo protect a class in a dataset, first move the label's image to a separate location and run Fawkes. Please\nuse `--debug` option and set `batch-size` to a reasonable number (i.e 16, 32). If the images are already cropped and\naligned, then also use the `no-align` option.\n\n### Citation\n\n```\n@inproceedings{shan2020fawkes,\n  title={Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models},\n  author={Shan, Shawn and Wenger, Emily and Zhang, Jiayun and Li, Huiying and Zheng, Haitao and Zhao, Ben Y},\n  booktitle={Proc. of {USENIX} Security},\n  year={2020}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FShawn-Shan%2Ffawkes","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FShawn-Shan%2Ffawkes","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FShawn-Shan%2Ffawkes/lists"}