REVIEW 6 cited by
FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Recent attacks on federated learning demonstrate that keeping the training data on clients' devices does not provide sufficient privacy, as the model parameters shared by clients can leak information about their training data. A 'secure aggregation' protocol enables the server to aggregate clients' models in a privacy-preserving manner. However, existing secure aggregation protocols incur high computation/communication costs, especially when the number of model parameters is larger than the number of clients participating in an iteration -- a typical scenario in federated learning. In this paper, we propose a secure aggregation protocol, FastSecAgg, that is efficient in terms of computation and communication, and robust to client dropouts. The main building block of FastSecAgg is a novel multi-secret sharing scheme, FastShare, based on the Fast Fourier Transform (FFT), which may be of independent interest. FastShare is information-theoretically secure, and achieves a trade-off between the number of secrets, privacy threshold, and dropout tolerance. Riding on the capabilities of FastShare, we prove that FastSecAgg is (i) secure against the server colluding with 'any' subset of some constant fraction (e.g. $\sim10\%$) of the clients in the honest-but-curious setting; and (ii) tolerates dropouts of a 'random' subset of some constant fraction (e.g. $\sim10\%$) of the clients. FastSecAgg achieves significantly smaller computation cost than existing schemes while achieving the same (orderwise) communication cost. In addition, it guarantees security against adaptive adversaries, which can perform client corruptions dynamically during the execution of the protocol.
Forward citations
Cited by 6 Pith papers
-
Images in Motion?: A First Look into Video Leakage in Collaborative Deep Learning
Gradient inversion recovers low-resolution frames from single-sample video gradients in federated learning, and super-resolution modestly improves fidelity against originals, while feature extractors resist the attack...
-
Asymptotically Optimal Secure Aggregation for Wireless Federated Learning with Multiple Servers
A multi-server wireless federated learning scheme combining secret sharing and artificial noise alignment achieves communication latency within a factor of 4 of the information-theoretic optimum, and is asymptotically...
-
Private Aggregation for Byzantine-Resilient Heterogeneous Federated Learning
Nearest neighbor mixing can be composed with secure aggregation and private information retrieval to give information-theoretic privacy and Byzantine resilience for heterogeneous federated learning.
-
Setup Once, Secure Always: A Single-Setup Secure Federated Learning Aggregation Protocol with Forward and Backward Secrecy for Dynamic Users
A single-setup secure aggregation protocol for federated learning that achieves forward and backward secrecy, dynamic user participation, and dropout tolerance using fresh random masks with a cyclic key-negation trick.
-
MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics
A gRPC micro-service FL stack with t-out-of-N CKKS secure aggregation matches cleartext accuracy on EMNIST and TCGA BRCA subtyping at modest extra cost for large models.
-
Secure Aggregation for Privacy-Preserving Federated Learning on Clinical EEG Data
Graph-based secure aggregation variants hide individual EEG model updates from the server in simulated cross-silo FL, remaining trainable while adding measurable compute and communication cost.
Discussion (0). Continue with ORCID to comment.