Publications

SECRYPT 2026 · position paper

MOSAIC-FL: a microservice based privacy-preserving framework with application to genomics

Paul Largillier, Karl Paygambar, Cédric Gouy-Pailler, Vincent Meyer, Mallek Sallami Mziou, Oana Stan

We present MOSAIC-FL, a modular and secure federated learning framework built around microservice orchestration. The secure aggregation protocol is based on a threshold variant of the CKKS homomorphic encryption scheme, enabling fault-tolerant privacy-preserving training. We demonstrate the framework on a genomics use case.

@inproceedings{largillier2026mosaic,
  title     = {{MOSAIC-FL}: a microservice based privacy-preserving framework with application to genomics},
  author    = {Largillier, Paul and Paygambar, Karl and Gouy-Pailler, C{\'e}dric and Meyer, Vincent and Sallami Mziou, Mallek and Stan, Oana},
  booktitle = {Proceedings of the 23rd International Conference on Security and Cryptography (SECRYPT 2026)},
  year      = {2026},
}