[Post-doctoral offer] Secure Distributed Learning in the Edge-Cloud continuum (M/F)

European Commission; France; Sur place; EUR 30 000 - 45 000; Plein temps

Résumé du poste

Une opportunité de recherche post-doctorale à la European Commission en France se concentre sur le développement d'algorithmes d'apprentissage fédéré, visant à renforcer la sécurité et la confidentialité des données. Le candidat retenu rejoindra l'équipe de recherche DRIM au LIRIS et contribuera à des solutions novatrices reliant l'edge et le cloud.

Qualifications

• PhD en Intelligence Artificielle avec préférence pour l'IA distribuée.
• Compétence dans les techniques de préservation de la vie privée.
• Connaissances en traitement de données sensibles et sécurité informatique.

Responsabilités

• Effectuer une revue de l'état de l'art sur les techniques d'apprentissage distribué.
• Proposer et mettre en œuvre une solution innovante d'apprentissage fédéré.
• Évaluer les performances et résilience de la solution contre les attaques.

Connaissances

Apprentissage fédéré

Algorithmique

Cryptographie

Formation

PhD en Intelligence Artificielle

Description du poste

Organisation/Company CNRS Department Laboratoire d'informatique en image et systèmes d'information Research Field Computer science Mathematics » Algorithms Researcher Profile First Stage Researcher (R1) Country France Application Deadline 16 Jul 2025 - 23:59 (UTC) Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 18 Aug 2025 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The handling of sensitive data is usually performed by a trusted machine that must first decrypt the stored data before processing it. This preliminary step creates a break in the secure storage-computation continuum. Furthermore, although data processing can be carried out in a hardware enclave, many operations, such as those related to machine learning, require the use of GPUs. This is the case, for example, for actors who wish to collaborate (e.g., through the training of a federated learning model) but do not trust each other to use a private and distributed learning tool on top of enclave-secured storage. The objective of this post-doctoral project is to develop privacy-preserving federated learning algorithms in the edge-cloud continuum. One promising approach is to leverage recent secure technologies such as NVIDIA confidential computing (GPUs combined with secure enclaves) to achieve this continuum.

• Conduct a state-of-the-art review of privacy-preserving distributed learning techniques in the edge-cloud continuum and identify the limitations of existing solutions.
• Propose a novel privacy-preserving federated learning solution within the edge-cloud continuum.
• Implement the proposed solution and evaluate its performance and resilience to attacks.
• Publish a paper presenting the obtained results

The postdoctoral researcher will join the DRIM team at LIRIS.

A PhD in AI with a preference to distributed AI is required.