FusionDP: Foundation Model-Assisted Differentially Private Learning for Partially Sensitive Features

Documenti analoghi

• De-identification is not enough: a comparison between de-identified and synthetic clinical notes
  di: Sarkar, Atiquer Rahman, et al.
  Pubblicazione: (2024)
• Robust Privacy Amidst Innovation with Large Language Models Through a Critical Assessment of the Risks
  di: Chuang, Yao-Shun, et al.
  Pubblicazione: (2024)
• SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation
  di: Xia, Yuyang, et al.
  Pubblicazione: (2025)
• DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
  di: Thareja, Rushil, et al.
  Pubblicazione: (2025)
• DP-BREM: Differentially-Private and Byzantine-Robust Federated Learning with Client Momentum
  di: Gu, Xiaolan, et al.
  Pubblicazione: (2023)