Aarhus University Seal

Eluding Secure Aggregation in Federated Learning via Model Inconsistency

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review


  • Dario Pasquini, Swiss Federal Institute of Technology Lausanne
  • ,
  • Danilo Francati
  • Giuseppe Ateniese, George Mason University

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. In this work, we show that a malicious server can easily elude secure aggregation as if the latter were not in place. We devise two different attacks capable of inferring information on individual private training datasets, independently of the number of users participating in the secure aggregation. This makes them concrete threats in large-scale, real-world federated learning applications. The attacks are generic and equally effective regardless of the secure aggregation protocol used They exploit a vulnerability of the federated learning protocol caused by incorrect usage of secure aggregation and lack of parameter validation. Our work demonstrates that current implementations of federated learning with secure aggregation offer only a ''false sense of security.''

Original languageEnglish
Title of host publicationCCS 2022 - Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security
Number of pages15
PublisherAssociation for Computing Machinery
Publication yearNov 2022
ISBN (Electronic)9781450394505
Publication statusPublished - Nov 2022
Event28th ACM SIGSAC Conference on Computer and Communications Security, CCS 2022 - Los Angeles, United States
Duration: 7 Nov 202211 Nov 2022


Conference28th ACM SIGSAC Conference on Computer and Communications Security, CCS 2022
LandUnited States
ByLos Angeles
SponsorACM Special Interest Group on Security, Audit, and Control (SIGSAC)
SeriesProceedings of the ACM Conference on Computer and Communications Security

Bibliographical note

Publisher Copyright:
© 2022 ACM.

    Research areas

  • federated learning, model inconsistency, secure aggregation

See relations at Aarhus University Citationformats

ID: 296340718