DMM: Distributed Matrix Mechanism for Differentially-Private Federated Learning Based on Constant-Overhead Linear Secret Resharing

Ähnliche Einträge

• TAPAS: Efficient Two-Server Asymmetric Private Aggregation Beyond Prio(+)
  von: Karthikeyan, Harish, et al.
  Veröffentlicht: (2026)
• Flamingo: Multi-Round Single-Server Secure Aggregation with Applications to Private Federated Learning
  von: Ma, Yiping, et al.
  Veröffentlicht: (2023)
• Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
  von: Zhou, Yvonne, et al.
  Veröffentlicht: (2024)
• $\mathsf{OPA}$: One-shot Private Aggregation with Single Client Interaction and its Applications to Federated Learning
  von: Karthikeyan, Harish, et al.
  Veröffentlicht: (2024)
• ZKBoost: Zero-Knowledge Verifiable Training for XGBoost
  von: Melissaris, Nikolas, et al.
  Veröffentlicht: (2026)