Research | Arkhn

La recherche en IA, Data & Privacy

La recherche en Intelligence Artificielle et la protection des données sont au coeur des valeurs de notre équipe. Retrouvez nos publications en IA, NLP et Data Privacy, en collaboration notamment avec l'ENS, l'INRIA, l'Imperial College London, l'université McGill et la fondation OpenMined.

📚 Publications

TESA: A Task in Entity Semantic Aggregation for Abstractive Summarization
EMNLP 2020
Clément Jumel, Annie Louis, Jackie C. K. Cheung
🧑‍💻 github.com/clementjumel/tesa
Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning
ArXiv Preprint 2020
Alexandre Tamborrino, Nicola Pellicano, Baptiste Pannier, Pascal Voitot, Louise Naudin
Health research and innovation: Can we optimize the interface between startups/pharmaceutical companies and academic health care institutions or not?
ArXiv Preprint 2020
Jean-François Dhainaut, Olivier Blin, ...,Corneliu Malciu
ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing
ArXiv Preprint 2020
Théo Ryffel, David Pointcheval, Francis Bach
🧑‍💻 github.com/LaRiffle/AriaNN
Privacy-preserving medical image analysis
Med-NeurIPS 2020
Alexander Ziller, Jonathan Passerat-Palmbach, Théo Ryffel, Dmitrii Usynin, Andrew Trask, Ionésio Da Lima Costa Junior, Jason Mancuso, Marcus Makowski, Daniel Rueckert, Rickmer Braren, Georgios Kaissis,
🧑‍💻 github.com/OpenMined/PySyft
Toward trustworthy AI development: mechanisms for supporting verifiable claims
ArXiv Preprint 2020
Miles Brundage, Shahar Avin, Jasmine Wang et al.
Partially Encrypted Machine Learning using Functional Encryption
NeurIPS 2019
Théo Ryffel, Edouard Dufour-Sans, Romain Gay, Francis Bach, David Pointcheval
🧑‍💻 github.com/LaRiffle/collateral-learning
A Generic Framework for Privacy Preserving Deep Learning
NeurIPS 2018 Workshop on Privacy-Preserving Machine Learning
Théo Ryffel, Andrew Trask, Morten Dahl, Bobby Wagner, Jason Mancuso, Daniel Rueckert, Jonathan Passerat-Palmbach
🧑‍💻 github.com/OpenMined/PySyft

✍️ Articles de blog

PySyft + Opacus: Federated Learning with Differential Privacy
by Théo Ryffel on September 30th, 2020
Encrypted inference with ResNet-18 using PyTorch + PySyft on ants & bees images
by Théo Ryffel on September 15th, 2020
Anonymisation vs pseudonymisation: don't be fooled anymore!
by Théo Ryffel on April 6th, 2020
Encrypted Deep Learning Training with Multi-Party Computation
by Théo Ryffel on August 5th, 2019
Encrypted Deep Learning Classification with PyTorch & PySyft
by Théo Ryffel on April 16th, 2019
Deep Learning & Federated Learning in 10 Lines of PyTorch + PySyft
by Théo Ryffel on March 1st, 2019

🎤 Talks

April 26, 2021
Meetup FHIR France #8: OSIRIS on FHIR: How to model large sets of clinical and genomic data for multi-centric oncology research
March 29, 2021
The Majors Originals #32 - Corneliu Malciu from Arkhn.
Watch again!
March 18, 2021
Talk on interactions between Differential Privacy and Multi-Party Computation at ENS Paris (internal).
March 16, 2021
Presentation of new tools for automated text analysis and structuration at AP-HP.
February 17, 2021
Presentation about data architectures in healthcare facilities and privacy enhancing techniques, at Roche.
February 17, 2021
Podcast: "Recruiting a technical team with expertise in data and healthcare". Listen the podcast
November 20, 2020
Talk about building a multi-Purpose stack using FHIR as a persistence layer, FHIR Dev Days 2020.
September 26, 2020
Talk at the OpenMined Privacy Conference about concrete applications of privacy in healthcare.
July 8, 2020
Presentation of privacy-preserving demos at Paris OpenMined Meetup
June 19, 2020
Talk on Federated Analytics on Real-life Healthcare Data at the Federated Learning Conference
December 10, 2019
Poster presentation at NeurIPS 2019, Partially Encrypted Machine Learning using Functional Encryption (Canada)
November 29, 2019
Semantic Web applied to healthcare, presentation at Datathon Archives Nationales
November 22, 2019
Talk at FHIR Dev Days: "Pyrog: an open-source mapping tool and ETL for FHIR"
October 15, 2019
Keynote on Data Anonymization at the BNP Paribas - Plug And Play Deep Dive
June 19, 2019
Talk at School of Cybersecurity - Université Côte d'Azur on OpenMined
June 6, 2019
Presentation "Tools for Safe AI" at Laboratoire de Sciences Cognitives et Psycholinguistiques (BabyCloud team)
Mai 15, 2019
Presentation of Federated Learning Techniques at ENS Paris
Mai 14, 2019
Talk at Paris Meetup OpenMined on Secure & Federated Learning at Arkhn
March 20, 2019
Talk at Paris Meetup OpenMined to present PySyft
December 8, 2018
Talk at Spotlight session NeurIPS 2018 Workshop on Privacy-Preserving Machine Learning (Canada)

Communauté Open Source

Les projets ambitieux ont besoin d'une communauté pour les soutenir
et ils doivent être accessibles au plus grand nombre

Venez discuter avec nous sur Slack pour découvrir nos dernières nouvelles et rejoindre le projet

Rejoignez-nous sur Github pour contribuer au développement d'Arkhn.

Restez au courant en nous suivant sur Twitter.

Nous soutenons la communauté OpenMined de Federated & Privacy-Preserving Machine Learning, en contribuant activement à la bibliothèque PySyft.