___       _   _                 
  / _ \_   _| |_| |__   ___  _ __  
 / /_)/ | | | __| '_ \ / _ \| '_ \ 
/ ___/| |_| | |_| | | | (_) | | | |
\/     \__, |\__|_| |_|\___/|_| |_|
       |___/  ___ _  __  __                     _   _       _ 
             /   (_)/ _|/ _| ___ _ __ ___ _ __ | |_(_) __ _| |
            / /\ / | |_| |_ / _ \ '__/ _ \ '_ \| __| |/ _` | |
           / /_//| |  _|  _|  __/ | |  __/ | | | |_| | (_| | |
          /___,' |_|_| |_|  \___|_|  \___|_| |_|\__|_|\__,_|_|
                       ___      _                       
                      / _ \_ __(_)_   ____ _  ___ _   _ 
                     / /_)/ '__| \ \ / / _` |/ __| | | |
                    / ___/| |  | |\ V / (_| | (__| |_| |
                    \/    |_|  |_| \_/ \__,_|\___|\__, |
                                                  |___/ 
--------------------------------------------------------------------------------

This repository shows some example implementations of differential privacy[1]
in Python via Jupyter Notebooks. Each notebook contains further references and
information. This work may contain blunders, and it's accuracy has not been
verified, however it should still be able to give you a good starting point
for work with differential privacy.

You can use nbviewer[2] or GitHub[3] to view the notebooks online.

This work was completed under the guidance of Praneeth Vepakomma [4]

1: https://en.wikipedia.org/wiki/Differential_privacy
2: https://nbviewer.org
3: https://github.com/acheam0/python_dp
4: https://praneeth.mit.edu/

--------------------------------------------------------------------------------

+-------+
| INDEX |
+-------+

- Approximate differential privacy (epsilon-delta):
    - gaussian_mechanism.ipynb
        
- Bayes rule:
    - bayesian_attacker.ipynb

- Choice query:
    - exponential_mechanism.ipynb

- Clipping:
    - laplace_example_class_height.ipynb

- Compositions:
    - gaussian_mechanism.ipynb
 
- Exponential mechanism:
    - exponential_mechanism.ipynb

- Histogram query:
    - laplace_mechanism.ipynb

- Helper functions:
    - common.py

- Privacy loss distributions:
    - gaussian_mechanism.ipynb

- Privacy loss random variable:
    - gaussian_mechanism.ipynb

- Pure differential privacy (epsilon):
    - laplace_example_class_height.ipynb
    - laplace_mechanism.ipynb

- Sum, count, mean queries:
    - laplace_example_class_height.ipynb
    - laplace_mechanism.ipynb

In addition to these, there are some incomplete notebooks in the "Incomplete/"
subdirectory.

--------------------------------------------------------------------------------
Copyright (c) 2023 Armaan Bhojwani <me@armaanb.net>, MIT License