From cbb5c1b6c90823e7cb31c74a73d7ea2c47c7a1b5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Viktor=20Sz=C3=A9pe?= Date: Sat, 25 Jul 2020 16:19:14 +0200 Subject: [PATCH] Add pypi link to README plus some *free* empty lines :) --- README.md | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 54e4992..8bd6ff4 100644 --- a/README.md +++ b/README.md @@ -10,6 +10,7 @@ If you would like to use Fawkes to protect your identity, please check out our b Copyright --------- + 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. @@ -39,11 +40,13 @@ when --mode is `custom`: `fawkes -d ./imgs --mode mid` ### 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 person, 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]`. -### How do I know my images are secure? +### How do I know my images are secure? + We are actively working on this. Python script that can test the protection effectiveness will be ready shortly. Quick Installation @@ -57,9 +60,10 @@ pip install fawkes If you don't have root privilege, please try to install on user namespace: `pip install --user fawkes`. - +[pypi_fawkes]: https://pypi.org/project/fawkes/ ### Citation + ``` @inproceedings{shan2020fawkes, title={Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models},