Star

Davidson, Alex; Snyder, Peter; Quirk, E. B.; Genereux, Joseph; Livshits, Benjamin; Haddadi, Hamed

doi:10.1145/3548606.3560631

Search citation statements

Order By: Relevance

Paper Sections

Select...

Related Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Book3

Other2

Article1

Relationship

Self Cite0

Independent6

Authors

Journals

Cited by 7 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Secure machine learning. Many approaches have been developed for machine learning without secure aggregation [10,14,16,26,31]. These approaches often ask clients to secret-share model updates between two servers, and run an MPC protocol between the two servers.…”

Section: Related Workmentioning

confidence: 99%

OLYMPIA: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols

Ngong¹,

Gibson²,

Near³

2023

Preprint

View full text Add to dashboard Cite

Recent secure aggregation protocols enable privacypreserving federated learning for high-dimensional models among thousands or even millions of participants. Due to the scale of these use cases, however, end-to-end empirical evaluation of these protocols is impossible. We present OLYMPIA, a framework for empirical evaluation of secure protocols via simulation. OLYMPIA provides an embedded domain-specific language for defining protocols, and a simulation framework for evaluating their performance. We implement several recent secure aggregation protocols using OLYMPIA, and perform the first empirical comparison of their end-to-end running times. We release OLYMPIA as open source.

show abstract