1

Scalable and Privacy-Preserving Federated Principal Component Analysis
Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the …
David Froelicher, Hyunghoon Cho, Manaswitha Edupalli, Joao Sa Sousa, Jean-Philippe Bossuat, Apostolos Pyrgelis, Juan R. Troncoso-Pastoriza, Jean-Pierre Hubaux
Cite PDF Link Trailer Video Video
Privacy-Preserving Federated Recurrent Neural Networks
We present RHODE, a novel system that enables privacy-preserving training of and prediction on Recurrent Neural Networks (RNNs) in a …
Sinem Sav, Abdulrahman Diaa, Apostolos Pyrgelis, Jean-Philippe Bossuat, Jean-Pierre Hubaux
PDF Cite DOI
Bootstrapping for Approximate Homomorphic Encryption with Negligible Failure-Probability by Using Sparse-Secret Encapsulation
Bootstrapping parameters for the approximate homomorphic-encryption scheme of Cheon et al., CKKS (Asiacrypt 17), are usually …
Jean-Philippe Bossuat, Juan R. Troncoso-Pastoriza, Jean-Pierre Hubaux
Cite Link PDF Video
Efficient Bootstrapping for Approximate Homomorphic Encryption with Non-sparse Keys
We present a bootstrapping procedure for the full-RNS variant of the approximate homomorphic-encryption scheme of Cheon et al., CKKS …
Jean-Philippe Bossuat, Christian Mouchet, Juan R. Troncoso-Pastoriza, Jean-Pierre Hubaux
Cite Link PDF Talk Video
Multiparty Homomorphic Encryption from Ring-Learning-with-Errors
We propose and evaluate a securemultiparty-computation (MPC) solution in the semihonest model with dishonest majority that is based on …
Christian Mouchet, Juan R. Troncoso-Pastoriza, Jean-Philippe Bossuat, Jean-Pierre Hubaux
Cite Link PDF Artifact Video
Scalable Privacy-Preserving Distributed Learning
In this paper, we address the problem of privacy-preserving training and evaluation of neural networks in an $N$-party, federated …
David Froelicher, Juan R. Troncoso-Pastoriza, Apostolos Pyrgelis, Sinem Sav, Joao Sa Sousa, Jean-Philippe Bossuat, Jean-Pierre Hubaux
Cite Link PDF Video Slides