Eluding Secure Aggregation in Federated Learning via Model Inconsistency
Dario Pasquini, Danilo Francati, Giuseppe Ateniese
2022Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security93 citationsDOIOpen Access PDF
Abstract
Secure aggregation is a cryptographic protocol that securely computes the aggregation of its inputs. It is pivotal in keeping model updates private in federated learning. Indeed, the use of secure aggregation prevents the server from learning the value and the source of the individual model updates provided by the users, hampering inference and data attribution attacks.
Topics & Concepts
Federated learningComputer scienceComputer securityDistributed computingPrivacy-Preserving Technologies in DataCryptography and Data SecurityStochastic Gradient Optimization Techniques