Publications by Jean-Pierre Hubaux

Secure and federated genome-wide association studies for biobank-scale datasets

Sharing data across institutions for genome-wide association studies (GWAS) would enhance the discovery of genetic variation linked to health and disease1,2. However, existing data-sharing regulations limit the scope of such collaborations3. Although crypt ...

NATURE PORTFOLIO2025

VERITAS: Plaintext Encoders for Practical Verifiable Homomorphic Encryption

Jean-Pierre Hubaux, Carmela González Troncoso, Christian Louis Knabenhans

Homomorphic encryption has become a practical solution for protecting the privacy of computations on sensitive data. However, existing homomorphic encryption pipelines do not guarantee the correctness of the computation result in the presence of a maliciou ...

Association for Computing Machinery, Inc2024

Scalable and Privacy-Preserving Federated Principal Component Analysis

Jean-Pierre Hubaux, Juan Ramón Troncoso-Pastoriza, Apostolos Pyrgelis, David Jules Froelicher, Joao André Gomes de Sá e Sousa, Jean-Philippe Léonard Bossuat

Principal component analysis (PCA) is an essential algorithm for dimensionality reduction in many data science domains. We address the problem of performing a federated PCA on private data distributed among multiple data providers while ensuring data confi ...

IEEE COMPUTER SOC2023

PELTA - Shielding Multiparty-FHE against Malicious Adversaries

Jean-Pierre Hubaux, Carmela González Troncoso, Sylvain Chatel, Christian Vincent Mouchet

Multiparty fully homomorphic encryption (MFHE) schemes enable multiple parties to efficiently compute functions on their sensitive data while retaining confidentiality. However, existing MFHE schemes guarantee data confidentiality and the correctness of th ...

Assoc Computing Machinery2023

Poster: Verifiable Encodings for Maliciously-Secure Homomorphic Encryption Evaluation

Jean-Pierre Hubaux, Carmela González Troncoso, Christian Louis Knabenhans, Sylvain Chatel

Homomorphic encryption has become a promising solution for protecting the privacy of computations on sensitive data. However, existing homomorphic encryption pipelines do not guarantee the correctness of the computation result in the presence of a maliciou ...

Assoc Computing Machinery2023

An Efficient Threshold Access-Structure for RLWE-Based Multiparty Homomorphic Encryption

Jean-Pierre Hubaux, Christian Vincent Mouchet

We propose and implement a multiparty homomorphic encryption (MHE) scheme with a t-out-of -N-threshold access-structure that is efficient and does not require a trusted dealer in the common random string model. We construct this scheme from the ring-learni ...

SPRINGER2023

slytHErin: An Agile Framework for Encrypted Deep Neural Network Inference

Jean-Pierre Hubaux, Apostolos Pyrgelis, Sinem Sav, Francesco Intoci

Homomorphic encryption (HE), which allows computations on encrypted data, is an enabling technology for confidential cloud computing. One notable example is privacy-preserving Prediction-as-a-Service (PaaS), where machine-learning predictions are computed ...

Springer Nature2023

System and method for privacy-preserving distributed training of neural network models on distributed datasets

Jean-Pierre Hubaux, Juan Ramón Troncoso-Pastoriza, David Jules Froelicher, Apostolos Pyrgelis, Joao André Gomes de Sá e Sousa, Jean-Philippe Léonard Bossuat, Sinem Sav

A computer-implemented method and a distributed computer system (100) for privacy- preserving distributed training of a global neural network model on distributed datasets (DS1 to DSn). The system has a plurality of data providers (DP1 to DPn) being commun ...

2022

Privacy-Preserving and Efficient Verification of the Outcome in Genome-Wide Association Studies

Jean-Pierre Hubaux, Juan Ramón Troncoso-Pastoriza, Erman Ayday, Apostolos Pyrgelis

2022

Privacy-preserving federated neural network learning for disease-associated cell classification

Jean-Pierre Hubaux, Sinem Sav

Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data silos. Sharing or centralizing the data of different healthcare institutions is, however, unfeasible or prohibitively difficult due t ...

ELSEVIER2022