Differentially Private Learning Needs Better Model Initialization and Self-Distillation

Documenti analoghi

• Position: Privacy Is Not Just Memorization!
  di: Mireshghallah, Niloofar, et al.
  Pubblicazione: (2025)
• Distributed HDMM: Scalable, Distributed, Accurate, and Differentially Private Query Workloads without a Trusted Curator
  di: Sedimo, Ratang, et al.
  Pubblicazione: (2025)
• Synthetic Data Can Mislead Evaluations: Membership Inference as Machine Text Detection
  di: Naseh, Ali, et al.
  Pubblicazione: (2025)
• Evaluating the Usability of Differential Privacy Tools with Data Practitioners
  di: Ngong, Ivoline C., et al.
  Pubblicazione: (2023)
• OLYMPIA: A Simulation Framework for Evaluating the Concrete Scalability of Secure Aggregation Protocols
  di: Ngong, Ivoline C., et al.
  Pubblicazione: (2023)