From 38f89999fa9c812275a719eb63ab134fef0f9ed0 Mon Sep 17 00:00:00 2001
From: Shawn Shan <shansixioing@uchicago.edu>
Date: Tue, 7 Jul 2020 11:58:54 -0500
Subject: [PATCH] Update README.md

Former-commit-id: 72004ca27135a362a197a6463b7b9372484993b5 [formerly 94e753f02cf470d95165e7347877328b17c82e5f]
Former-commit-id: c6a20cbd15c7d4c0d05ecdbf7c73008ce114fdfb
---
 README.md | 56 ++++++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 45 insertions(+), 11 deletions(-)

diff --git a/README.md b/README.md
index d60e85b..14729ef 100644
--- a/README.md
+++ b/README.md
@@ -1,21 +1,55 @@
-# Fawkes
+Fawkes
+------
 
-Fawkes is a privacy protection system developed by researchers at 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/).  
 
-We published an academic paper to summary our work "[Fawkes: Protecting Personal Privacy against Unauthorized Deep Learning Models](https://arxiv.org/pdf/2002.08327.pdf)" at *USENIX Security 2020*. 
-
-
-### BEFORE YOU RUN OUR CODE
+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*. 
 
 If you would like to use Fawkes to protect your images, please check out our binary implementation on the [website](http://sandlab.cs.uchicago.edu/fawkes/#code). 
 
-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). 
 
 
-### INSTALL FAWKES
-Fawkes can be installed with pip. Simply run: 
-`pip install fawkes`
+Usage
+-----
 
+`$ fawkes`
+
+Options:
+
+* `-m`, `--mode`       : the tradeoff between privacy and perturbation size
+* `-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 
+* `--format`      : format of the output image. 
+
+when --mode is `custom`: 
+* `--th`       : perturbation threshold
+* `--max-step`       : number of optimization steps to run 
+* `--lr`       : learning rate for the optimization
+* `--feature-extractor` : name of the feature extractor to use
+* `--separate_target`   : whether select separate targets for each faces in the diectory. 
+
+
+
+
+
+### Tips
+
+- Select the best mode for your need. `Low` protection is effective against most model trained by individual trackers with commodity face recongition model. `mid` is robust against most commercial models, such as Facebook tagging system. `high` is robust against powerful modeled trained using different face recongition API. 
+- 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. 
+
+
+Quick Installation
+------------------
+
+Install from [PyPI][pypi_fawkes]:
+
+```
+pip install fawkes
+```
+
+If you don't have root privilege, please try to install on user namespace: `pip install --user fawkes`.
 
 ### Citation
 ```
@@ -25,4 +59,4 @@ Fawkes can be installed with pip. Simply run:
   booktitle="Proc. of USENIX Security",
   year={2020}
 }
-```
\ No newline at end of file
+```