.. 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-td2a-ml-crypted: Machine Learning sur des données cryptées +++++++++++++++++++++++++++++++++++++++++ *Notebooks* .. toctree:: :maxdepth: 2 ../notebooks/_gs2a_crypt *Lectures* * `Fully Homomorphic Encryption over the Integers `_ * `Homomorphic Encryption from Learning with Errors: Conceptually-Simpler, Asymptotically-Faster, Attribute-Based `_ * `Differentially Private Online Learning `_ * `A Differentially Private Stochastic Gradient Descent Algorithm for Multiparty Classification `_ * `Machine Learning Classification over Encrypted Data `_ * `CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy `_ * `Compressed Sensing `_ * `ML Confidential: Machine Learning on Encrypted Data `_ * `Encrypted statistical machine learning: new privacy preserving methods `_ * `Fast and Secure Linear Regression and Biometric Authentication with Security Update `_ * `NuCypher KMS: Decentralized key management system `_ * `Hawk: The Blockchain Model of Cryptography and Privacy-Preserving Smart Contracts `_ * `Privacy-Preserving Classification on Deep Neural Network `_ * `Awesome Homomorphic Encryption `_ * `Cryptotree : fast and accurate predictions on encrypted structured data `_ *2021* * `Enclaves as accelerators: learning lessons from GPU computing for designing efficient runtimes for enclaves `_ * `Collisions in MD5... and how to use them for fun and profit `_ * `On the Security of Authentication Protocols for the Web `_ *Lectures - alternatives* * `Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data `_ * `Practical Black-Box Attacks against Machine Learning `_ * `awesome-differential-privacy `_ *Lectures - MPC* * `awesome-mpc `_ (Multi-Party Computation) *Modules* * `CrypTen `_ : l'approche la plus prometteuse par Facebook * `ciphermed `_, pas maintenu par l'auteur mais un peu plus par d'autres `ciphermed-forests `_ * `PySyft `_ : encrypted deep learning library * `python-paillier (phe) `_ : a library for partially homomorphic encryption in python, cette librairie fait du machine learning en clair une fois les données et le modèle décryptées, elle promet de faire `mieux `_ * `PySEAL `_ (`SEAL `_, `PySEAL: A Python wrapper implementation of the SEAL homomorphic encryption library `_) * `cryptotree `_