.. image:: pyeco.png
    :height: 20
    :alt: Economie
    :target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-economiste

.. image:: pystat.png
    :height: 20
    :alt: Statistique
    :target: http://www.xavierdupre.fr/app/ensae_teaching_cs/helpsphinx/td_2a_notions.html#pour-un-profil-plutot-data-scientist

.. _l-mlanomprivacy:

Anonymisation des données / Privacy
+++++++++++++++++++++++++++++++++++

*(à venir)*

*Lectures*

* `A General Survey Of Privacy-Preserving Data Mining Models And Algorithms <http://charuaggarwal.net/generalsurvey.pdf>`_
* `Privacy Preserving Data Mining <http://web.stanford.edu/group/mmds/slides/mcsherry-mmds.pdf>`_, Cynthia Dwork, Frank McSherry,
  concept de :math:`\epsilon`-differential privacy
  (`version longue <https://users.soe.ucsc.edu/~abadi/CS223_F12/mcsherry.pdf>`_,
  `Privacy Preserving Data Mining <http://www.cs.jhu.edu/~fabian/courses/CS600.624/slides/privacy-preserving.pdf>`_)
* `Differentially Private Empirical Risk Minimization <http://www.jmlr.org/papers/volume12/chaudhuri11a/chaudhuri11a.pdf>`_
* `Preserving Privacy of Continuous High-dimensional Data with Minimax Filters <http://www.jmlr.org/proceedings/papers/v38/hamm15.pdf>`_
* `Privacy for Free: Posterior Sampling and Stochastic Gradient Monte Carlo <http://www.jmlr.org/proceedings/papers/v37/wangg15.pdf>`_
* `Privatics (INRIA) <https://team.inria.fr/privatics/>`_
* `Differential Privacy for Bayesian Inference through Posterior Sampling∗ <http://www.jmlr.org/papers/volume18/15-257/15-257.pdf>`_
* `Corrupt Bandits for Preserving Local Privacy <https://arxiv.org/abs/1708.05033>`_
* `A General Approach to Adding Differential Privacy to Iterative Training Procedures
  <https://arxiv.org/pdf/1812.06210.pdf>`_
* `Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
  <https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8466590>`_

*Articles*

* `Differential Privacy Series Part 1 | DP-SGD Algorithm Explained
  <https://medium.com/pytorch/differential-privacy-series-part-1-dp-sgd-algorithm-explained-12512c3959a3>`_
* `Calibrating Noise to Sensitivity in Private Data Analysis
  <https://iacr.org/archive/tcc2006/38760266/38760266.pdf>`_
* `The Algorithmic Foundations of Differential Privacy
  <https://www.cis.upenn.edu/~aaroth/Papers/privacybook.pdf>`_

*Tables rondes*

* `La protection des données personnelles en assurance dialogue du juriste avec l'actuaire <https://f-origin.hypotheses.org/wp-content/blogs.dir/253/files/2018/02/DAR.pdf>`_

*Lectures - autodestruction*

* `New Directions for Self-Destructing Data Systems <https://vanish.cs.washington.edu/pubs/vanish-extensions-techreport11.pdf>`_
* `Keypad: An Auditing File System for Theft-Prone Devices <http://eurosys2011.cs.uni-salzburg.at/pdf/eurosys2011-geambasu.pdf>`_
* `Self Destructing Data System Based On Session Keys <http://www.ijstr.org/final-print/feb2014/Self-Destructing-Data-System-Based-On-Session-Keys.pdf>`_
* `Vanish: Increasing Data Privacy with Self-Destructing Data <http://www.usenix.net/legacy/events/sec09/tech/full_papers/geambasu.pdf>`_

*Données résiduelles dans les modèles*

* `The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets <https://arxiv.org/pdf/1802.08232.pdf>`_

*Algorithmes*

* `k-anonymité <https://en.wikipedia.org/wiki/K-anonymity>`_
* `L-diversité <https://en.wikipedia.org/wiki/L-diversity>`_

*Modules*

* `AGD Tools <https://github.com/SGMAP-AGD/anonymisation>`_ : ce module s'accompagne d'un wiki et de notebooks.
* `tensorflow/privacy <https://github.com/tensorflow/privacy>`_
* `whitenoise <https://github.com/opendifferentialprivacy/whitenoise-core-python>`_,
  *WhiteNoise Core Differential Privacy Library Python Bindings*
* `opacus <https://opacus.ai/>`_