RISE Research Radar

Computer Science Open House 2022-2025

2023

Scalable Privacy-Preserving Federated Machine Learning

Apostolos Pyrgelis

Summary

Scalable Privacy-Preserving Federated Machine Learning Analytics. Using multi-party homomorphic encryption (MHE) and federated learning for data confidentiality. Supports GLMs, MLPs, CNNs, RNNs, and PCA. Workflow-specific optimizations for scalability.

Themes

federated-learningprivacy

Keywords

federated learning, homomorphic encryption, privacy-preserving ML, MHE, scalability

Poster

Scalable Privacy-Preserving Federated Machine Learning poster

Click image to open full size