Leveraging Randomness in Model and Data Partitioning for Privacy Amplification

Documenti analoghi

• Less Random, More Private: What is the Optimal Subsampling Scheme for DP-SGD?
  di: Dong, Andy, et al.
  Pubblicazione: (2026)
• Training generative models from privatized data
  di: Reshetova, Daria, et al.
  Pubblicazione: (2023)
• Universal Exact Compression of Differentially Private Mechanisms
  di: Liu, Yanxiao, et al.
  Pubblicazione: (2024)
• Privacy Amplification for Matrix Mechanisms
  di: Choquette-Choo, Christopher A., et al.
  Pubblicazione: (2023)
• Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
  di: Schuchardt, Jan, et al.
  Pubblicazione: (2024)