Secure Decentralized Learning

Saclay

CEA

Le CEA est un acteur majeur de la recherche, au service de l'État, de l'économie et des citoyens. Il apporte des solutions concrètes à leurs besoins dans quatre domaines principaux : transition énergétique, transition numérique, technologies...

View all jobs at CEA

Apply now Apply later

General information

Organisation

The French Alternative Energies and Atomic Energy Commission (CEA) is a key player in research, development and innovation in four main areas :
• defence and security,
• nuclear energy (fission and fusion),
• technological research for industry,
• fundamental research in the physical sciences and life sciences.

Drawing on its widely acknowledged expertise, and thanks to its 16000 technicians, engineers, researchers and staff, the CEA actively participates in collaborative projects with a large number of academic and industrial partners.

The CEA is established in ten centers spread throughout France
  

Reference

2024-33978  

Position description

Category

Mathematics, information, scientific, software

Contract

Internship

Job title

Secure Decentralized Learning - Internship H/F

Subject

The goal of this internship is to explore the combination of Multi-Party Computation (MPC) and Differential Privacy (DP) to assess the feasibility and effectiveness of these approaches in ensuring confidentiality.

Contract duration (months)

6

Job description

Context: Machine learning plays a central role in many applications, and the increasing adoption of decentralized solutions, combined with dependability requirements, necessitates that learning tasks be carried out in a decentralized manner. In such settings, nodes in the system can assume multiple roles: performing learning on their local data while also aggregating the computational results of other nodes.


In this context, we aim to achieve confidentiality, ensuring that private local data is not leaked while providing a practical solution.


Objective: The goal of this internship is to explore the combination of Multi-Party Computation (MPC) and Differential Privacy (DP) to assess the feasibility and effectiveness of these approaches in ensuring confidentiality.


Our team has previously conducted an exploratory study on MPC in the Federated Learning context, which provides a strong foundation for studying the integration of Differential Privacy techniques.


The successful candidate will join the Laboratory for Trustworthy, Smart, and Self-Organizing Information Systems (LICIA) at CEA LIST, working in a multicultural, multidisciplinary environment with the opportunity to collaborate with external researchers.


Methodology: The intern will be responsible for the following tasks:


Become familiar with the Differential Privacy principles.
Conduct a state-of-the-art review of Differential Privacy in Federated Learning and its combination with Multi-Party Computation.
Become familiar with the MPC solution developed in the laboratory.
Select a Differential Privacy approach and design a solution to integrate it with the existing MPC solution.
Implement the integrated solution.
Evaluate the performance of the solution.
 


Requirements:


Background in computer science or a related field, with a focus or strong interest in distributed systems, cryptography, and machine learning.
Programming skills in languages commonly used for cryptographic or machine learning tasks (e.g., Python, C++, or Rust).
Comfortable working in English, both for communication and documentation purposes.

Position location

Site

Saclay

Job location

France, Ile-de-France, Essonne (91)

Location

Palaiseau

Candidate criteria

Prepared diploma

Bac+5 - Diplôme École d'ingénieurs

PhD opportunity

Oui

Requester

Position start date

01/03/2025

Apply now Apply later
Job stats:  0  0  0

Tags: Computer Science Distributed Systems Industrial Machine Learning Mathematics PhD Privacy Python Research Rust Security

Region: Europe
Country: France

More jobs like this

Explore more career opportunities

Find even more open roles below ordered by popularity of job title or skills/products/technologies used.