Combining homomorphic encryption and differential privacy in federated learning - CEA - Commissariat à l’énergie atomique et aux énergies alternatives Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Combining homomorphic encryption and differential privacy in federated learning

Résumé

Recent works have investigated the relevance and practicality of using techniques such as Differential Privacy (DP) or Homomorphic Encryption (HE) to strengthen training data privacy in the context of Federated Learning protocols. As these two techniques cover different sources of confidentiality threats (other clients/end-users for the former, aggregation server for the latter), there is a need to consistently combine them in order to bridge the gap towards more realistic deployment scenarios. In this paper, we achieve that goal by means of a novel stochastic quantization operator which allows us to establish DP guarantees when the noise is both quantized and bounded due to the use of HE. The paper is concluded by experiments on the FEMNIST dataset which show that the precision required to get state-of-the art privacy/utility trade-off (which directly impacts HE parameters and, hence, HE operations performances) results in a computation time overhead between 0.2% and 1.1% imputable to HE (depending on the key setup, either single key or threshold), for the whole training of a 500k parameters model and state-of-the-art privacy/utility trade-off.
Fichier sous embargo
Fichier sous embargo
0 4 1
Année Mois Jours
Avant la publication
mercredi 28 août 2024
Fichier sous embargo
mercredi 28 août 2024
Connectez-vous pour demander l'accès au fichier

Dates et versions

cea-04485721 , version 1 (01-03-2024)

Identifiants

Citer

Arnaud Grivet Sebert, Marina Checri, Oana Stan, Renaud Sirdey, Cedric Gouy-Pailler. Combining homomorphic encryption and differential privacy in federated learning. 2023 20th Annual International Conference on Privacy, Security and Trust (PST), Aug 2023, Copenhague, Denmark. 10320195 (7 p.), ⟨10.1109/PST58708.2023.10320195⟩. ⟨cea-04485721⟩
21 Consultations
2 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More