Federated Learning Test Platform with Trusted Execution Environments

• Grant number: 25/12088-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2025
• End date: June 30, 2026
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Luis Henrique Maciel Kosmalski Costa
• Grantee: João Pedro Moretti Fontes Ferreira
• Host Institution: Instituto Alberto Luiz Coimbra de Pós-Graduação e Pesquisa (COPPE). Universidade Federal do Rio de Janeiro (UFRJ). Ministério da Educação (Brasil)
• Associated research grant: 23/00673-7 - Distributed intelligence in communications networks and in the internet of things, AP.TEM

Abstract

Federated learning suffers from recent adversarial attacks that compromise its privacy and training integrity. Trusted Execution Environments (TEE) are a new way to enforce privacy and integrity on untrusted hosts, even if privileged users act maliciously. TEEs have been widely used in the application of federated learning against adversarial attacks, and among the proposed TEE solutions, Intel SGX is one of the most widely used. This work aims to study and implement secure federated learning through the use of trusted execution environments in federated learning. (AU)