GenF: Federated Learning as a Service (FLaaS) with Generative AI

Generative AI to improve Federated Learning
Thematic area: Projects, Tech
Financing: ICSC Innovation Grants
Enabling Technology: Artificial Intelligence, Machine Learning

GenF aims to extend FLaaS by incorporating generative AI features to enhance privacy and model training in FL. Peers within the federation initially train only on synthetic data, and knowledge exchange employs rehearsal-based methods. The privacy preserving synthesis process involves navigating latent spaces of generative models to obfuscate sensitive data. This innovation targets security gaps in conventional FL systems, offering a privacy-focused solution for healthcare applications.

Italian Research Center on High Performance Computing Big Data and Quantum Computing (ICSC), project funded by European Union – NextGenerationEU – and National Recovery and Resilience Plan (NRRP) – Mission 4 Component 2. 

The goal

The main goal is to extend FLaaS by enhancing peer learning capabilities. This is achievable by harnessing the transformative potential of generative AI to foster a privacy-preserving, data-driven distributed learning strategy.  

The initial challenge

Improving the state of the art on privacy-preserving generative AI and FL. After gaining an overview of the most effective methods for privacy-preserving data synthesis, the projects aims to integrate Generative AI on the FLaaS prototype. 

The solution

The integration of Generative AI results in an advanced FLaaS prototype: this will enable the prototype to have better and more effective features for privacy-preserving distributed learning.  

Benefits

Some expected results will be:  

  • Contributing to the broader scientific community’s understanding of the potential applications and benefits of FLaaS in healthcare settings and   
  • Advancing the vision of federated learning in the clinical domain  
  • Fostering collaborative advancements in privacy preserving machine learning. 

On industries, the enhanced FLaaS prototype is poised to position itself as a pioneering force in the federated learning market. It is, as of now, aimed to involve clinical centers in partaking in federated learning without direct sharing of sensitive patient data, thus supporting the creation of more robust and precise predictive models. 

Partners

Participating Spoke

Spoke 1

 

For further information, please contact: barbara.vecchi@ifabfoundation.org

Sustainable Development Goals

Share on:

You may also be interested in:

Stay updated on the latest IFAB events and projects.Subscribe to our monthly newsletter