REVIEW 2 cited by
DP-SIGNSGD: When Efficiency Meets Privacy and Robustness
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
read the original abstract
Federated learning (FL) has emerged as a promising collaboration paradigm by enabling a multitude of parties to construct a joint model without exposing their private training data. Three main challenges in FL are efficiency, privacy, and robustness. The recently proposed SIGNSGD with majority vote shows a promising direction to deal with efficiency and Byzantine robustness. However, there is no guarantee that SIGNSGD is privacy-preserving. In this paper, we bridge this gap by presenting an improved method called DP-SIGNSGD, which can meet all the aforementioned properties. We further propose an error-feedback variant of DP-SIGNSGD to improve accuracy. Experimental results on benchmark image datasets demonstrate the effectiveness of our proposed methods.
Forward citations
Cited by 2 Pith papers
-
Information-Theoretically Secure Aggregation for Lightweight Federated Learning: Resilient to Dropouts and Adversaries
A secure aggregation protocol for sign-based federated learning computes the majority vote in one round with linear offline cost, but the claimed degree-halving simplification breaks at zero inputs and for inverse terms.
-
Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning
Hi-SAFE privately computes the signSGD majority vote using a Fermat-based indicator polynomial evaluated with Beaver triples, and uses subgrouping to keep per-user cost independent of n.
Discussion (0). Continue with ORCID to comment.