2020-02897 - Intern Visit in Privacy-Preserving, Federated Machine learning with Applications to Speech (H/F)
Le descriptif de l’offre ci-dessous est en Anglais

Niveau de diplôme exigé : Bac + 5 ou équivalent

Autre diplôme apprécié : This internship targets ongoing PhD students looking for a research visit

Fonction : Stagiaire de la recherche

A propos du centre ou de la direction fonctionnelle

The Inria Lille - Nord Europe Research Centre was founded in 2008 and employs a staff of 360, including 300 scientists working in sixteen research teams. Recognised for its outstanding contribution to the socio-economic development of the Hauts-De-France région, the Inria Lille - Nord Europe Research Centre undertakes research in the field of computer science in collaboration with a range of academic, institutional and industrial partners.

 The strategy of the Centre is to develop an internationally renowned centre of excellence with a significant impact on the City of Lille and its surrounding area. It works to achieve this by pursuing a range of ambitious research projects in such fields of computer science as the intelligence of data and adaptive software systems. Building on the synergies between research and industry, Inria is a major contributor to skills and technology transfer in the field of computer science.

Contexte et atouts du poste

The recruited intern will join the Inria Magnet research team:


Mission confiée

The recruited intern will work under the supervision of Aurélien Bellet (Inria researcher).

He/she will be involved in research activites related to privacy-preserving machine learning, federated machine learning and decentralized machine learning, with applications to speech technologies, see Magnet website for more details on ongoing work and projects:


Principales activités

  • Study how existing techniques for privacy-preserving machine learning (such as those based on adversarial training) can be applied/adapted to privacy for speech data, in particuliar in federated and decentralized settings.
  • Design and analyze new approaches that learn more personalized models (such as those recently developed in Magnet), and empirically study their ability to sustain attacks from adversarial participants.
  • Implement the algorithms and conduct some experimentations using public speech datasets to assess their practical utility, privacy protection and robustness to attacks from adversarial participants.
  • Write and submit papers to international conferences, describing the work above.
  • Present the work to collaborators in related projects, such as ANR Deep-Privacy and H2020 Comprise.


Mandatory skills : good fundamental knowledge and practice of machine learning (in particular deep learning)

Optional skills: knowledge of privacy-enhancing technologies and speech applications

Language : English


  • Subsidized meals
  • Partial reimbursement of public transport costs
  • Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
  • Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
  • Professional equipment available (videoconferencing, loan of computer equipment, etc.)
  • Social, cultural and sports events and activities
  • Access to vocational training
  • Social security coverage