A Secure Federated Learning framework using Homomorphic Encryption and Verifiable Computing
Résumé
In this paper, we present the first Federated Learning (FL) framework which is secure against both confidentiality and integrity threats from the aggregation server, in the case where the resulting model is not disclosed to the latter. We do so by combining Homomorphic Encryption (HE) and Verifiable Computing (VC) techniques in order to perform a Federated Averaging operator directly in the encrypted domain (by means of HE) and produce formal proofs that the operator was correctly applied (by means of VC). Due to the simplicity of the aggregation function, we are able to ground our approach in additive HE techniques which are highly mature in terms of security and decently efficient. We also introduce a number of optimizations which allows to reach practical execution performances on the larger deep learning models end of the spectrum. The paper also provides extensive experimental results on the FEMNIST dataset demonstrating that the approach preserves the quality of the resulting models at the cost of practically meaningful computing and communication overheads, at least in the cross-silo setting for which higher-end machines can be involved on both the client and server sides.
Mots clés
Artificial intellience
machine learning
federated learning
online learning
Trustworthy Artificial intelligence
Homomorphic Encryption
Encryption
confidentiality
integrity threat
aggregation server
Verifiable Computing
Federated Averaging operator
formal proofs
aggregation function
security
deep learning
FEMNIST dataset
Data privacy
Data analysis
Automation
Computational modeling
Big Data
Collaborative work
Verifiable Computation
Secure Federated Learning
Secure Federated
Client-side
Server Side
Server Aggregates
Training Data
Common Practice
Decoding
Global Model
Calculation Of Function
Updated Model
Dataset Identifier
Security Analysis
Encrypted Data
Central Server
Cryptosystem
Differential Privacy
Local Updates
Multi-party Computation
Training Round
Encryption Scheme
Security Proof
Encrypted Message
Cryptographic Primitives
Algorithm Checks
Final Model
Fichier principal
article_AbbassMadi_A Secure Federated Learning framework using_Homomorphic Encryption and Verifiable Computing.pdf (603.57 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)